Claude Cursor Skill

tweakidea

Use when a founder wants to evaluate a startup idea or problem, improve or compare idea evaluations, or mine Hacker News for product opportunities. Runs a 14-dimension weighted scorecard with assumption tracking, generates small/medium/big idea tweaks, diffs runs, browses and ana

LLM Mart · 0 points · 2 views 190 listing impressions 0 install-command copies
Download eph5xx-tweakidea-skills_tweakidea-007ebb9.zip · 107 KB

Install

skills CLI npx skills add https://github.com/eph5xx/tweakidea/tree/main/skills/tweakidea
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install eph5xx-tweakidea@llmmart
Git git clone https://github.com/eph5xx/tweakidea.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole eph5xx/tweakidea collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

TweakIdea helps founders make better decisions: evaluate whether a problem is worth solving, or discover which problems are emerging from technology shifts. Be an honest second opinion, not a cheerleader.

Setup

  1. SKILL_DIR is the directory that contains this SKILL.md (the runtime reports it as the skill's base directory). If no base directory is reported, use the first of $(pwd)/.claude/skills/tweakidea, $HOME/.claude/skills/tweakidea, $(pwd)/.agents/skills/tweakidea, or $HOME/.agents/skills/tweakidea that contains SKILL.md. Every {SKILL_DIR} path in this skill and its references resolves against it.
  2. Runtime: read references/runtime.md and map each capability it lists (ask-user, spawn-subagent, web-search, read-file, and the rest) and each model tier to what your runtime provides. The references name capabilities, not tools.
  3. HOME_DIR is the output of echo "$HOME". All user data lives under {HOME_DIR}/.tweakidea/.
  4. Python helpers in {SKILL_DIR}/scripts/ run through uv run. If a command needs them and uv is missing, tell the user to install it (brew install uv or curl -LsSf https://astral.sh/uv/install.sh | sh) and stop.

Routing

The invocation arguments are:

$ARGUMENTS

If the line above is still an unsubstituted placeholder (a dollar sign followed by the word ARGUMENTS), your runtime does not substitute arguments: use the text after the skill name in the user's invoking message instead.

Split them into COMMAND (the first word) and ARGS (everything after it). Command references use ARGS wherever they need the user's input.

  • No arguments: show the Commands table below and ask which command to run (ask-user with evaluate, improve, browse-hn, list; free text covers the rest). Never auto-run a command.
  • First word is a command name: read that command's reference and follow it exactly, with ARGS as its input.
  • Anything else: treat the full argument text as an idea and run evaluate with it as ARGS.

Commands

Command Arguments What it does Reference
evaluate idea text, file path, or empty 14 independent evaluators produce a weighted scorecard with assumption tracking and an HTML/markdown report references/commands/evaluate.md
improve run timestamp, prefix, or latest Three concrete idea tweaks (small reframe, medium reshape, big reimagine) grounded in the scoring rubrics references/commands/improve.md
diff two runs (timestamps, prefixes, or latest) Side-by-side comparison of two runs: score deltas, potential shifts, per-dimension movers references/commands/diff.md
browse-hn [topic] [today\|week\|month\|all] Search HN via Algolia and rank threads worth feeding into analyze-hn-post references/commands/browse-hn.md
analyze-hn-post HN URL or item id Analyze one HN discussion for technology shifts and product opportunities references/commands/analyze-hn-post.md
list optional category, limit, or filter List runs, HN analyses, and founder profiles under ~/.tweakidea/ references/commands/list.md
show timestamp, latest, HN id, founder, keyword, or query Find and open any artifact under ~/.tweakidea/ references/commands/show.md
share timestamp, latest, keyword, or query Upload a run's report.html to a secret GitHub gist and print shareable URLs references/commands/share.md

Internal references

Loaded by the commands above when needed; not invoked directly.

Reference Used by Contents
references/runtime.md all commands, setup Capability names, their Claude Code tools, fallbacks, and model tiers
references/agents/ti-researcher.md evaluate Web research subagent (competitive, market, user clusters)
references/agents/ti-extractor.md evaluate Hypothesis extraction subagent
references/agents/ti-evaluator.md evaluate Single-dimension evaluator subagent, spawned 14 times
references/agents/ti-narrative.md evaluate Cross-dimensional narrative subagent
references/scoring/EVALUATION.md evaluate, improve, agents Dimension Registry, weights, evidence tiers, scoring algorithm, verdict thresholds
references/scoring/dimensions/ evaluate, improve One rubric and signal table per dimension (14 files)
references/founder.md evaluate FOUNDER.md template, creation questions, fit questions, update rules
references/report.md render_report.py Report template data and rendering contract
references/hn.md browse-hn, analyze-hn-post Usage of hnparse.py and hnsearch.py

Scripts and assets

Path Purpose
scripts/compute.py Deterministic scorecard aggregation into numbers.json
scripts/render_report.py Renders report.md and report.html from a run directory
scripts/hnparse.py Fetches one HN post (article + comment tree)
scripts/hnsearch.py Searches HN posts via Algolia
scripts/lib/ Shared helpers: registry parsing, schema validation, error codes
assets/schemas/ JSON schemas for every pipeline artifact
assets/report/ Jinja2 report templates and CSS

Rules

  • Evaluate all 14 dimensions. Never skip, merge, or remove one.
  • Each evaluator works without seeing other dimensions' results, and each run starts from a clean context.
  • Pass founder profile data (~/.tweakidea/FOUNDER.md and fit answers) only to the Founder-Market Fit evaluator.
  • Pipeline artifacts are typed JSON validated against assets/schemas/. Do not parse agent output in the orchestrator; scripts/compute.py does all aggregation.
Files (tweakidea)
  • assets
    • report
      • styles.css 27.7 KB · in bundle
      • template.html.j2 23.6 KB · in bundle
      • template.md.j2 4.2 KB · in bundle
    • schemas
      • assumptions.json 973 B
        Loading…
      • dimension-evaluation.json 3.1 KB
        Loading…
      • hypotheses.json 948 B
        Loading…
      • idea.json 1.5 KB
        Loading…
      • next-steps.json 1.3 KB
        Loading…
      • numbers.json 4.9 KB
        Loading…
      • potential.json 2.1 KB
        Loading…
      • research.json 2.4 KB
        Loading…
      • strengths-weaknesses.json 918 B
        Loading…
      • version.json 1.3 KB
        Loading…
  • references
    • agents
      • ti-evaluator.md 15 KB
        Loading…
      • ti-extractor.md 4.5 KB
        Loading…
      • ti-narrative.md 10.3 KB
        Loading…
      • ti-researcher.md 6.7 KB
        Loading…
    • commands
      • analyze-hn-post.md 9.1 KB
        Loading…
      • browse-hn.md 5.7 KB
        Loading…
      • diff.md 6.3 KB
        Loading…
      • evaluate.md 26.4 KB
        Loading…
      • improve.md 9.2 KB
        Loading…
      • list.md 2.4 KB
        Loading…
      • share.md 2.3 KB
        Loading…
      • show.md 2.8 KB
        Loading…
    • scoring
      • dimensions
        • behavior-change-required.md 2.9 KB
          Loading…
        • clarity-of-target-customer.md 2.4 KB
          Loading…
        • defensibility.md 2.8 KB
          Loading…
        • founder-market-fit.md 3 KB
          Loading…
        • frequency.md 2.4 KB
          Loading…
        • incumbent-indifference.md 2.5 KB
          Loading…
        • mandatory-nature.md 2.2 KB
          Loading…
        • market-growth.md 2.1 KB
          Loading…
        • market-size.md 2.5 KB
          Loading…
        • pain-intensity.md 2.4 KB
          Loading…
        • scalability.md 2.3 KB
          Loading…
        • solution-gap.md 2.6 KB
          Loading…
        • urgency.md 2.1 KB
          Loading…
        • willingness-to-pay.md 2.4 KB
          Loading…
      • EVALUATION.md 3.3 KB
        Loading…
    • founder.md 6.4 KB
      Loading…
    • hn.md 1.8 KB
      Loading…
    • report.md 6.6 KB
      Loading…
    • runtime.md 5.9 KB
      Loading…
  • scripts
    • lib
      • errors.py 1.8 KB
        Loading…
      • registry.py 2.2 KB
        Loading…
      • schema.py 1.5 KB
        Loading…
      • __init__.py 0 B
        Loading…
    • compute.py 8.7 KB
      Loading…
    • hnparse.py 8 KB
      Loading…
    • hnsearch.py 5.1 KB
      Loading…
    • render_report.py 5.9 KB
      Loading…
  • SKILL.md 7 KB
    ---
    name: tweakidea
    description: "Use when a founder wants to evaluate a startup idea or problem, improve or compare idea evaluations, or mine Hacker News for product opportunities. Runs a 14-dimension weighted scorecard with assumption tracking, generates small/medium/big idea tweaks, diffs runs, browses and analyzes HN threads, and lists, opens, or shares artifacts saved under ~/.tweakidea/."
    license: MIT
    compatibility: "Works in any Agent Skills client. evaluate needs subagents plus web search and web fetch; the other commands run inline. Requires uv and network access; share also needs the GitHub CLI (gh). Tuned and tested on Claude Code with Sonnet and Opus."
    allowed-tools: Read Write Bash Glob Agent AskUserQuestion
    ---
    
    TweakIdea helps founders make better decisions: evaluate whether a problem is worth solving, or discover which problems are emerging from technology shifts. Be an honest second opinion, not a cheerleader.
    
    ## Setup
    
    1. **SKILL_DIR** is the directory that contains this SKILL.md (the runtime reports it as the skill's base directory). If no base directory is reported, use the first of `$(pwd)/.claude/skills/tweakidea`, `$HOME/.claude/skills/tweakidea`, `$(pwd)/.agents/skills/tweakidea`, or `$HOME/.agents/skills/tweakidea` that contains `SKILL.md`. Every `{SKILL_DIR}` path in this skill and its references resolves against it.
    2. **Runtime:** read [references/runtime.md](references/runtime.md) and map each capability it lists (`ask-user`, `spawn-subagent`, `web-search`, `read-file`, and the rest) and each model tier to what your runtime provides. The references name capabilities, not tools.
    3. **HOME_DIR** is the output of `echo "$HOME"`. All user data lives under `{HOME_DIR}/.tweakidea/`.
    4. Python helpers in `{SKILL_DIR}/scripts/` run through `uv run`. If a command needs them and `uv` is missing, tell the user to install it (`brew install uv` or `curl -LsSf https://astral.sh/uv/install.sh | sh`) and stop.
    
    ## Routing
    
    The invocation arguments are:
    
    $ARGUMENTS
    
    If the line above is still an unsubstituted placeholder (a dollar sign followed by the word ARGUMENTS), your runtime does not substitute arguments: use the text after the skill name in the user's invoking message instead.
    
    Split them into **COMMAND** (the first word) and **ARGS** (everything after it). Command references use `ARGS` wherever they need the user's input.
    
    - **No arguments:** show the Commands table below and ask which command to run (`ask-user` with `evaluate`, `improve`, `browse-hn`, `list`; free text covers the rest). Never auto-run a command.
    - **First word is a command name:** read that command's reference and follow it exactly, with ARGS as its input.
    - **Anything else:** treat the full argument text as an idea and run `evaluate` with it as ARGS.
    
    ## Commands
    
    | Command | Arguments | What it does | Reference |
    |---|---|---|---|
    | `evaluate` | idea text, file path, or empty | 14 independent evaluators produce a weighted scorecard with assumption tracking and an HTML/markdown report | [references/commands/evaluate.md](references/commands/evaluate.md) |
    | `improve` | run timestamp, prefix, or `latest` | Three concrete idea tweaks (small reframe, medium reshape, big reimagine) grounded in the scoring rubrics | [references/commands/improve.md](references/commands/improve.md) |
    | `diff` | two runs (timestamps, prefixes, or `latest`) | Side-by-side comparison of two runs: score deltas, potential shifts, per-dimension movers | [references/commands/diff.md](references/commands/diff.md) |
    | `browse-hn` | `[topic] [today\|week\|month\|all]` | Search HN via Algolia and rank threads worth feeding into `analyze-hn-post` | [references/commands/browse-hn.md](references/commands/browse-hn.md) |
    | `analyze-hn-post` | HN URL or item id | Analyze one HN discussion for technology shifts and product opportunities | [references/commands/analyze-hn-post.md](references/commands/analyze-hn-post.md) |
    | `list` | optional category, limit, or filter | List runs, HN analyses, and founder profiles under `~/.tweakidea/` | [references/commands/list.md](references/commands/list.md) |
    | `show` | timestamp, `latest`, HN id, `founder`, keyword, or query | Find and open any artifact under `~/.tweakidea/` | [references/commands/show.md](references/commands/show.md) |
    | `share` | timestamp, `latest`, keyword, or query | Upload a run's `report.html` to a secret GitHub gist and print shareable URLs | [references/commands/share.md](references/commands/share.md) |
    
    ## Internal references
    
    Loaded by the commands above when needed; not invoked directly.
    
    | Reference | Used by | Contents |
    |---|---|---|
    | [references/runtime.md](references/runtime.md) | all commands, setup | Capability names, their Claude Code tools, fallbacks, and model tiers |
    | [references/agents/ti-researcher.md](references/agents/ti-researcher.md) | `evaluate` | Web research subagent (competitive, market, user clusters) |
    | [references/agents/ti-extractor.md](references/agents/ti-extractor.md) | `evaluate` | Hypothesis extraction subagent |
    | [references/agents/ti-evaluator.md](references/agents/ti-evaluator.md) | `evaluate` | Single-dimension evaluator subagent, spawned 14 times |
    | [references/agents/ti-narrative.md](references/agents/ti-narrative.md) | `evaluate` | Cross-dimensional narrative subagent |
    | [references/scoring/EVALUATION.md](references/scoring/EVALUATION.md) | `evaluate`, `improve`, agents | Dimension Registry, weights, evidence tiers, scoring algorithm, verdict thresholds |
    | [references/scoring/dimensions/](references/scoring/dimensions/) | `evaluate`, `improve` | One rubric and signal table per dimension (14 files) |
    | [references/founder.md](references/founder.md) | `evaluate` | FOUNDER.md template, creation questions, fit questions, update rules |
    | [references/report.md](references/report.md) | `render_report.py` | Report template data and rendering contract |
    | [references/hn.md](references/hn.md) | `browse-hn`, `analyze-hn-post` | Usage of `hnparse.py` and `hnsearch.py` |
    
    ## Scripts and assets
    
    | Path | Purpose |
    |---|---|
    | [scripts/compute.py](scripts/compute.py) | Deterministic scorecard aggregation into `numbers.json` |
    | [scripts/render_report.py](scripts/render_report.py) | Renders `report.md` and `report.html` from a run directory |
    | [scripts/hnparse.py](scripts/hnparse.py) | Fetches one HN post (article + comment tree) |
    | [scripts/hnsearch.py](scripts/hnsearch.py) | Searches HN posts via Algolia |
    | [scripts/lib/](scripts/lib/) | Shared helpers: registry parsing, schema validation, error codes |
    | [assets/schemas/](assets/schemas/) | JSON schemas for every pipeline artifact |
    | [assets/report/](assets/report/) | Jinja2 report templates and CSS |
    
    ## Rules
    
    - Evaluate all 14 dimensions. Never skip, merge, or remove one.
    - Each evaluator works without seeing other dimensions' results, and each run starts from a clean context.
    - Pass founder profile data (`~/.tweakidea/FOUNDER.md` and fit answers) only to the Founder-Market Fit evaluator.
    - Pipeline artifacts are typed JSON validated against `assets/schemas/`. Do not parse agent output in the orchestrator; `scripts/compute.py` does all aggregation.
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.