extract-signal
An elastic signal-extraction methodology run under /multi-agent-mode. INFERS from the call what signal, what form, what stakes, and where output goes. Default is agentic — the root coordinates freshly-primed gathering and separate review workers; when extract-signal IS the agent
Install
npx skills add https://github.com/allemaar/open-skills/tree/main/skills/extract-signal
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install allemaar-open-skills@llmmart
git clone https://github.com/allemaar/open-skills.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole allemaar/open-skills collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
/extract-signal
An elastic methodology for turning a noisy source surface into a vetted signal in the form the requester asked for, without contaminating the context that must stay clean. It is a goal + a toolkit + the judgment to compose techniques to fit the task — not a fixed pipeline. The work it does is determined by the context it is invoked with.
Operational owner: this
SKILL.md.protocol.yonis its aligned declarative companion. When either changes, update the other and refresh the@STAMPdate.
The principle that motivates this skill
Context hygiene comes from RELOCATION, not TRUNCATION. Noisy work happens where noise is cheap — a spawned sub-agent's window, or this skill's own disposable window when it is itself a sub-agent. Only the signal reaches the place that must stay clean. The gathering area is never shrunk to fit an arbitrary size.
Inference & contracts (read the call, don't demand a form)
The skill infers its parameters from how it was invoked; explicit overrides are accepted but never required:
- What signal — the question to answer.
- What form — the output shape (see menu). Inferred from the ask ("as a risk-list", "is it ready?", "what are the options").
- Stakes — inferred from consequence; drives vetting depth.
- Mode & output — inferred per below.
Modes & output (inferred)
- Agentic (default — the normal call). The root agent owns composition, gathering dispatch and review dispatch. Invoke selected
prime-*skills at the root, so their workers are leaves. For a cold opinion, the root dispatches a separate sibling reviewer with the question, primary-source pointers and artifact, without the gatherer's conclusions or lead rationale. Gatherers and reviewers never orchestrate each other. The root integrates and returns the signal inline unless a file is specified. - In-session / new-session (it IS the agent). extract-signal gathers and vets directly as the running agent; output inline by default, to a file if specified. (When it is itself a dispatched sub-agent, this is the same path: it works inline in its disposable window and does NOT spawn further sub-agents — depth-1 guardrail; the isolation already protects the caller.) In a leaf, use the bounded direct-gather procedure from its primed brief, not a
prime-*invocation that requires another worker. Run permitted vetting inline with nested delegation suppressed. Disclose same-context dependence; it is not a cold opinion. If material vetting requires an independent opinion, return findings and that unmet requirement to the root before a readiness verdict.
The methodology (elastic — compose, don't follow blindly)
- Frame the inferred signal request (what · form · stakes).
- Compose the technique set for this task and run it (in the mode above):
- Gather —
/prime-sweep(many sources) ·/prime-fetch(one noisy call) ·/prime-expand(vague request → questions + named sources first). - Diverge —
/insight-explorewhen the signal needs options/hypotheses generated before they can be vetted. - Vet —
/insight-critique(poke holes) →/insight-assess(evidence solid? what does it imply?). - Cold opinion — a fresh, no-prior-framing read (
/cold-review-style) as a drift guard.
- Gather —
- Vet proportionally to stakes — cheap/low-stakes → a quick critique may suffice; material/high-stakes → full critique + assess + cold opinion. Reach for the cold opinion whenever the lead has been deep in the material.
- Present the signal in the requested form (next two sections govern how).
Output contract — the signal carries its provenance
Whatever the form, the presentation MUST include:
- the signal in the requested form;
- provenance —
source:line(or equivalent) for load-bearing claims; - confidence + residual gaps (what wasn't determined and why);
- which techniques ran (so the caller can judge the vetting depth).
Sensitivity vs destination (do not over-expose the signal)
Signal inherits the sensitivity of what it was extracted from. Before presenting:
- Tag the signal's sensitivity (e.g. internal / restricted / public).
- The destination must be cleared for that sensitivity. If the output is bound for a lower-trust or external/public destination than the signal warrants, flag it and withhold the sensitive parts rather than present them. Never let internal detail flow into a public-bound artifact by default.
Failure & contradiction handling
- Empty gather → report "no signal found", with what was searched. Never fabricate signal to fill the form.
- Vet disagreement (
/insight-assessvs the cold opinion) → surface the split with both positions; do not silently average to a false consensus. - Mid-flight blocker — if extraction hits a decision only the caller/handler can make, surface it and pause that line; do not guess past it.
Bounds
- Concurrency — the root owns at most 3 parallel leaf workers, depth-1. Every composed technique inherits that limit; an active mode owns dispatch rather than adding another layer.
- Termination — before work, bind finite tool-call, wave and elapsed-time limits to the invocation. Before dispatch also bind monitoring, cancellation and terminal success/failure/timeout outcomes. Without those controls, stop the dependent agentic route. Stop at the first exhausted bound or no-new-signal wave; retain partial findings and name capped or unperformed vetting. Do not retry or extend automatically.
Signal forms (reference menu — any custom form allowed)
| Form | Typically pairs |
|---|---|
| verdict / yes-no | gather → critique → assess (+ cold if material) |
| ranked options | insight-explore → assess → present ranked |
| risk-list | prime-fetch/sweep → critique → present risks |
| map / inventory | prime-sweep → present structured map |
| count / metric | prime-fetch → verify → present number + method |
| bill-of-health | prime-sweep → critique → assess → cold → present report |
Examples (illustrative — the lead composes to fit the actual call)
1 · Agentic + high-stakes → bill-of-health
Call:
extract-signal: is @acme/parser ready to ship publicly?Infers: signal = release-readiness · form = bill-of-health · stakes = high · mode = agentic (default) · output = inline to caller. Composes: root invokesprime-sweepto dispatch leaf gathering → root applies inline critique and assess → root dispatches a separate cold sibling reviewer → root returns the bill-of-health. Returns: verdict + per-area findings withsource:line, confidence, residual gaps, techniques-run.
2 · In-session inline + options → ranked-options
Call (running as the session):
extract-signal: what are our options for the cache layer? inline.Infers: form = ranked-options · stakes = moderate · mode = in-session (it IS the agent) · output = inline. Composes:insight-explore(3+ options) →insight-assess(score) → present ranked. Lighter vet — no cold opinion at moderate stakes. Returns: ranked options + rationale + provenance + gaps.
3 · Output-to-file + moderate → risk-list
Call:
extract-signal: risks in this diff → write to risks.mdInfers: form = risk-list · output = file (risks.md) · stakes = moderate · mode = agentic. Composes:prime-fetchthe diff →insight-critique(hunt risks) → write a severity-ranked risk-list to the file. Writes:risks.md— each risk with severity +source:line+ confidence.
4 · Sensitivity-edge (the guard fires)
Call:
extract-signal: summarize the auth module for the public READMEInfers: signal sensitivity = internal · destination = public README. Acts: sensitivity (internal) > destination (public) → withhold internal detail, flag it — present only the public-safe surface and tell the caller what was withheld and why. Never auto-leaks internal detail into a public artifact.
Rules
- MUST infer the signal request from the call; MUST NOT demand a rigid input form.
- MUST default to root-owned agentic gathering and sibling review; when it IS the agent, work inline with output inline-by-default or to a file if specified.
- MUST keep gathered output complete (report-to-file for large surfaces); MUST NOT impose an arbitrary word/size cap on gathering.
- MUST compose techniques to fit the task; MUST NOT run a fixed sequence regardless of the signal.
- MUST vet before presenting; depth MUST scale with stakes.
- MUST attach provenance + confidence + gaps + techniques-run to the presented signal.
- MUST sensitivity-match the signal to its destination; MUST NOT over-expose internal signal to a public/external destination.
- MUST surface (not average) vet disagreements and (not guess past) mid-flight blockers.
- MUST NOT spawn sub-agents from within a sub-agent (depth-1 guardrail).
Pairs with
/prime-sweep,/prime-fetch,/prime-expand— gather techniques./insight-explore— divergent generation when candidates are needed first./insight-critique,/insight-assess— the vetting engine./cold-review— the second-cold-opinion shape./multi-agent-mode— the session posture this runs inside./caller-options— surfaces the venue/output/form choices.
Evolution (logged for v2+)
A signal ledger/cache (reuse prior extractions) and signal-quality metrics are deferred — not yet in scope.
Human output. This skill's handler-facing output obeys the human-output contract (
human-output/SKILL.md).
Self-improvement. On completion, run the Self-Improvement Protocol (
self-improve/SKILL.md): apply its signal taxonomy and threshold to this run; surface any surviving proposal for handler approval. Conservative — silent otherwise. Never auto-apply.
Files (open-skills)
-
protocol.yon 5.7 KB · in bundle
-
SKILL.md 11.8 KB
--- name: extract-signal description: > An elastic signal-extraction methodology run under /multi-agent-mode. INFERS from the call what signal, what form, what stakes, and where output goes. Default is agentic — the root coordinates freshly-primed gathering and separate review workers; when extract-signal IS the agent (in-session / new-session) it works inline with output inline by default (or to a file if specified). Composes techniques per task: gather (/prime-sweep, /prime-fetch, /prime-expand), diverge (/insight-explore), vet (/insight-critique → /insight-assess), cold second opinion (/cold-review-style). Vetting scales with stakes; the presented signal carries provenance and is sensitivity-matched to its destination. Trigger on /extract-signal, "extract the signal on X and present it as Y", "gather + vet + report the signal about X". Not the prime-* / insight-* / cold-review skills it composes; not /multi-agent-mode (the mode it runs under). visibility: public self-improvable: true triggers: - "/extract-signal" - "extract the signal on X and present it as Y" - "gather + vet + report the signal about X" next-skills: - skill: insight-assess phrase: "/insight-assess" why: "Evaluate and decide among the options the extracted signal surfaced" - skill: plan-create phrase: "/plan-create" why: "Turn the vetted signal into a phased implementation plan" - skill: handoff phrase: "/handoff" why: "Package the extracted, provenance-tagged signal as a brief for a fresh agent" - skill: human-merge phrase: "/human-merge" why: "Several sub-agents each returned their own signal report — collapse reports drawn from the same upstream source into the single source they are, and name the conflicts between them, before any of it reaches a person" - skill: human-rewrite phrase: "/human-rewrite" why: "When the destination is a person rather than an agent — make the signal readable while provenance, confidence and stated gaps all survive the pass" --- # /extract-signal An **elastic methodology** for turning a noisy source surface into a **vetted signal in the form the requester asked for**, without contaminating the context that must stay clean. It is a goal + a toolkit + the judgment to **compose techniques to fit the task** — not a fixed pipeline. The work it does is determined by the context it is invoked with. > **Operational owner:** this `SKILL.md`. [`protocol.yon`](protocol.yon) is its aligned declarative companion. When either changes, update the other and refresh the `@STAMP` date. ## The principle that motivates this skill **Context hygiene comes from RELOCATION, not TRUNCATION.** Noisy work happens where noise is cheap — a spawned sub-agent's window, or this skill's own disposable window when it is itself a sub-agent. Only the **signal** reaches the place that must stay clean. The gathering area is never shrunk to fit an arbitrary size. ## Inference & contracts (read the call, don't demand a form) The skill **infers** its parameters from how it was invoked; explicit overrides are accepted but never required: - **What signal** — the question to answer. - **What form** — the output shape (see menu). Inferred from the ask ("as a risk-list", "is it ready?", "what are the options"). - **Stakes** — inferred from consequence; drives vetting depth. - **Mode & output** — inferred per below. ## Modes & output (inferred) - **Agentic (default — the normal call).** The root agent owns composition, gathering dispatch and review dispatch. Invoke selected `prime-*` skills at the root, so their workers are leaves. For a cold opinion, the root dispatches a separate sibling reviewer with the question, primary-source pointers and artifact, without the gatherer's conclusions or lead rationale. Gatherers and reviewers never orchestrate each other. The root integrates and returns the signal inline unless a file is specified. - **In-session / new-session (it IS the agent).** extract-signal gathers and vets directly as the running agent; **output inline by default**, **to a file if specified**. (When it is itself a dispatched sub-agent, this is the same path: it works inline in its disposable window and does NOT spawn further sub-agents — depth-1 guardrail; the isolation already protects the caller.) In a leaf, use the bounded direct-gather procedure from its primed brief, not a `prime-*` invocation that requires another worker. Run permitted vetting inline with nested delegation suppressed. Disclose same-context dependence; it is not a cold opinion. If material vetting requires an independent opinion, return findings and that unmet requirement to the root before a readiness verdict. ## The methodology (elastic — compose, don't follow blindly) 1. **Frame** the inferred signal request (what · form · stakes). 2. **Compose** the technique set for this task and run it (in the mode above): - **Gather** — `/prime-sweep` (many sources) · `/prime-fetch` (one noisy call) · `/prime-expand` (vague request → questions + named sources first). - **Diverge** — `/insight-explore` when the signal needs options/hypotheses generated before they can be vetted. - **Vet** — `/insight-critique` (poke holes) → `/insight-assess` (evidence solid? what does it imply?). - **Cold opinion** — a fresh, no-prior-framing read (`/cold-review`-style) as a drift guard. 3. **Vet proportionally to stakes** — cheap/low-stakes → a quick critique may suffice; material/high-stakes → full critique + assess + cold opinion. Reach for the cold opinion whenever the lead has been deep in the material. 4. **Present** the signal in the requested form (next two sections govern *how*). ## Output contract — the signal carries its provenance Whatever the form, the presentation MUST include: - the **signal** in the requested form; - **provenance** — `source:line` (or equivalent) for load-bearing claims; - **confidence** + **residual gaps** (what wasn't determined and why); - **which techniques ran** (so the caller can judge the vetting depth). ## Sensitivity vs destination (do not over-expose the signal) Signal inherits the sensitivity of what it was extracted from. Before presenting: - **Tag the signal's sensitivity** (e.g. internal / restricted / public). - **The destination must be cleared for that sensitivity.** If the output is bound for a lower-trust or external/public destination than the signal warrants, **flag it and withhold the sensitive parts** rather than present them. Never let internal detail flow into a public-bound artifact by default. ## Failure & contradiction handling - **Empty gather** → report "no signal found", with what was searched. Never fabricate signal to fill the form. - **Vet disagreement** (`/insight-assess` vs the cold opinion) → **surface the split** with both positions; do not silently average to a false consensus. - **Mid-flight blocker** — if extraction hits a decision only the caller/handler can make, **surface it and pause** that line; do not guess past it. ## Bounds - **Concurrency** — the root owns at most 3 parallel leaf workers, depth-1. Every composed technique inherits that limit; an active mode owns dispatch rather than adding another layer. - **Termination** — before work, bind finite tool-call, wave and elapsed-time limits to the invocation. Before dispatch also bind monitoring, cancellation and terminal success/failure/timeout outcomes. Without those controls, stop the dependent agentic route. Stop at the first exhausted bound or no-new-signal wave; retain partial findings and name capped or unperformed vetting. Do not retry or extend automatically. ## Signal forms (reference menu — any custom form allowed) | Form | Typically pairs | |---|---| | verdict / yes-no | gather → critique → assess (+ cold if material) | | ranked options | insight-explore → assess → present ranked | | risk-list | prime-fetch/sweep → critique → present risks | | map / inventory | prime-sweep → present structured map | | count / metric | prime-fetch → verify → present number + method | | bill-of-health | prime-sweep → critique → assess → cold → present report | ## Examples (illustrative — the lead composes to fit the actual call) **1 · Agentic + high-stakes → bill-of-health** > **Call:** `extract-signal: is @acme/parser ready to ship publicly?` > **Infers:** signal = release-readiness · form = bill-of-health · stakes = high · mode = agentic (default) · output = inline to caller. > **Composes:** root invokes `prime-sweep` to dispatch leaf gathering → root applies inline critique and assess → root dispatches a separate cold sibling reviewer → root returns the bill-of-health. > **Returns:** verdict + per-area findings with `source:line`, confidence, residual gaps, techniques-run. **2 · In-session inline + options → ranked-options** > **Call (running as the session):** `extract-signal: what are our options for the cache layer? inline.` > **Infers:** form = ranked-options · stakes = moderate · mode = in-session (it IS the agent) · output = inline. > **Composes:** `insight-explore` (3+ options) → `insight-assess` (score) → present ranked. Lighter vet — no cold opinion at moderate stakes. > **Returns:** ranked options + rationale + provenance + gaps. **3 · Output-to-file + moderate → risk-list** > **Call:** `extract-signal: risks in this diff → write to risks.md` > **Infers:** form = risk-list · output = file (`risks.md`) · stakes = moderate · mode = agentic. > **Composes:** `prime-fetch` the diff → `insight-critique` (hunt risks) → write a severity-ranked risk-list to the file. > **Writes:** `risks.md` — each risk with severity + `source:line` + confidence. **4 · Sensitivity-edge (the guard fires)** > **Call:** `extract-signal: summarize the auth module for the public README` > **Infers:** signal sensitivity = internal · destination = public README. > **Acts:** sensitivity (internal) > destination (public) → **withhold internal detail, flag it** — present only the public-safe surface and tell the caller what was withheld and why. Never auto-leaks internal detail into a public artifact. ## Rules - MUST infer the signal request from the call; MUST NOT demand a rigid input form. - MUST default to root-owned agentic gathering and sibling review; when it IS the agent, work inline with output inline-by-default or to a file if specified. - MUST keep gathered output complete (report-to-file for large surfaces); MUST NOT impose an arbitrary word/size cap on gathering. - MUST compose techniques to fit the task; MUST NOT run a fixed sequence regardless of the signal. - MUST vet before presenting; depth MUST scale with stakes. - MUST attach provenance + confidence + gaps + techniques-run to the presented signal. - MUST sensitivity-match the signal to its destination; MUST NOT over-expose internal signal to a public/external destination. - MUST surface (not average) vet disagreements and (not guess past) mid-flight blockers. - MUST NOT spawn sub-agents from within a sub-agent (depth-1 guardrail). ## Pairs with - **`/prime-sweep`, `/prime-fetch`, `/prime-expand`** — gather techniques. - **`/insight-explore`** — divergent generation when candidates are needed first. - **`/insight-critique`, `/insight-assess`** — the vetting engine. - **`/cold-review`** — the second-cold-opinion shape. - **`/multi-agent-mode`** — the session posture this runs inside. - **`/caller-options`** — surfaces the venue/output/form choices. ## Evolution (logged for v2+) A signal ledger/cache (reuse prior extractions) and signal-quality metrics are deferred — not yet in scope. > **Human output.** This skill's handler-facing output obeys the human-output > contract (`human-output/SKILL.md`). > **Self-improvement.** On completion, run the Self-Improvement Protocol (`self-improve/SKILL.md`): apply its signal taxonomy and threshold to this run; surface any surviving proposal for handler approval. Conservative — silent otherwise. Never auto-apply.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.