Claude Skill

insight-skill-gap

Scan recent work and identify if new skills should be created or existing ones updated. Trigger when the user runs /skill-gap, asks to "check for skill gaps", "what skills should we add", "did we miss anything worth capturing", or after /retro flags patterns worth codifying. Use

LLM Mart · 0 points · 0 views 0 listing impressions 0 install-command copies
Download allemaar-open-skills-skills_insight-skill-gap-acf5f79.zip · 4 KB

Install

skills CLI npx skills add https://github.com/allemaar/open-skills/tree/main/skills/insight-skill-gap
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install allemaar-open-skills@llmmart
Git 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

/skill-gap

Identify gaps in the skill library based on recent implementation work — propose new skills or updates to existing ones.

Structured execution spec: protocol.yon. Read it for the canonical rules and step sequence; this file is explanation. The two must stay in sync — if you edit one, update the other and refresh the @STAMP date.

Skill Discovery Protocol — ensures reusable patterns don't stay buried in implementation code.

Phase 1 — Recent Work Scan

  1. Gather recent context — conversation history, changed files, new patterns introduced. Summarize: what was built, which libraries/frameworks were used, what novel patterns emerged.
  2. Load skill index — Resolve the actual supplied or host/repository skill catalog and record its scope before duplicate checking. If unavailable, keep candidates provisional and explicitly mark duplicate coverage incomplete; a missing index is never an empty library.

Phase 2 — Gap Analysis

Cross-reference patterns from Phase 1 against the skill index. Classify each pattern:

  • (A) Skill exists and covers it — no action
  • (B) Skill exists but is incomplete — propose update; specify which sections are missing or outdated
  • (C) No skill exists — evaluate against new-skill criteria below

Criteria for a new skill:

  • Pattern is reusable (used 2+ times, or clearly will be)
  • Pattern involves non-obvious decisions or gotchas
  • Pattern spans multiple files or concepts

Gate: gap analysis must be documented before proceeding.

Phase 3 — Skill Proposals

For each gap, draft a skill specification:

  • Skill name — domain-prefix convention (e.g., drizzle-*, nextjs16-*)
  • Skill family — domain prefix
  • Prerequisites — what the user needs to know first
  • Complexity estimate — how large/involved the skill content will be
  • Key sections to cover — what the skill should teach

Check skill-smith for template requirements before drafting. Present proposals to the user and wait for approval before proceeding.

Phase 4 — Execution (only if approved)

Create approved skills and apply approved targeted updates through Skill Smith’s selected create or update/write route. Preserve exact existing approval, canonical ownership, preimages and affected references; approval does not replace write prerequisites.

Rules

  • MUST verify no existing skill covers the same domain before proposing a new one.
  • MUST follow the domain-prefix naming convention.
  • MUST specify which sections are missing or outdated when proposing updates.
  • MUST check skill-smith for template requirements before proposing new skills.
  • MUST NOT propose skills for one-off patterns with no reuse potential.
  • SHOULD recommend immediate creation (not deferral) when reuse potential is HIGH.

Next Steps

  • /skill-smith — to build approved skills

Human output. This skill's handler-facing output obeys the human-output contract (human-output/SKILL.md).

Next skills. On completion, run the Next Skills protocol (next-skills/SKILL.md): surface the next-skills recommendations from front-matter for the caller to pick. Offer only — never auto-invoke.

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 5.4 KB · in bundle
  • SKILL.md 4.1 KB
    ---
    name: insight-skill-gap
    description: >
      Scan recent work and identify if new skills should be created or existing ones updated. Trigger when the user runs /skill-gap, asks to "check for skill gaps", "what skills should we add", "did we miss anything worth capturing", or after /retro flags patterns worth codifying. Use insight-retro for a broader post-implementation retrospective.
    visibility: public
    self-improvable: true
    next-skills:
      - skill: skill-smith
        phrase: "/skill-smith"
        why: "Scaffold the new skill the gap analysis identified"
    triggers:
      - "/skill-gap"
      - "check for skill gaps"
      - "what skills should we add"
      - "did we miss anything worth capturing"
    ---
    
    # /skill-gap
    
    Identify gaps in the skill library based on recent implementation work — propose new skills or updates to existing ones.
    
    > **Structured execution spec:** [`protocol.yon`](protocol.yon). Read it for the canonical rules and step sequence; this file is explanation. The two must stay in sync — if you edit one, update the other and refresh the `@STAMP` date.
    
    > **Skill Discovery Protocol — ensures reusable patterns don't stay buried in implementation code.**
    
    ## Phase 1 — Recent Work Scan
    
    1. **Gather recent context** — conversation history, changed files, new patterns introduced. Summarize: what was built, which libraries/frameworks were used, what novel patterns emerged.
    2. **Load skill index** — Resolve the actual supplied or host/repository skill catalog and record its scope before duplicate checking. If unavailable, keep candidates provisional and explicitly mark duplicate coverage incomplete; a missing index is never an empty library.
    
    ## Phase 2 — Gap Analysis
    
    Cross-reference patterns from Phase 1 against the skill index. Classify each pattern:
    
    - **(A) Skill exists and covers it** — no action
    - **(B) Skill exists but is incomplete** — propose update; specify which sections are missing or outdated
    - **(C) No skill exists** — evaluate against new-skill criteria below
    
    **Criteria for a new skill:**
    
    - Pattern is reusable (used 2+ times, or clearly will be)
    - Pattern involves non-obvious decisions or gotchas
    - Pattern spans multiple files or concepts
    
    **Gate:** gap analysis must be documented before proceeding.
    
    ## Phase 3 — Skill Proposals
    
    For each gap, draft a skill specification:
    
    - **Skill name** — domain-prefix convention (e.g., `drizzle-*`, `nextjs16-*`)
    - **Skill family** — domain prefix
    - **Prerequisites** — what the user needs to know first
    - **Complexity estimate** — how large/involved the skill content will be
    - **Key sections to cover** — what the skill should teach
    
    Check `skill-smith` for template requirements before drafting. Present proposals to the user and wait for approval before proceeding.
    
    ## Phase 4 — Execution (only if approved)
    
    Create approved skills and apply approved targeted updates through Skill Smith’s selected create or update/write route. Preserve exact existing approval, canonical ownership, preimages and affected references; approval does not replace write prerequisites.
    
    ## Rules
    
    - MUST verify no existing skill covers the same domain before proposing a new one.
    - MUST follow the domain-prefix naming convention.
    - MUST specify which sections are missing or outdated when proposing updates.
    - MUST check `skill-smith` for template requirements before proposing new skills.
    - MUST NOT propose skills for one-off patterns with no reuse potential.
    - SHOULD recommend immediate creation (not deferral) when reuse potential is HIGH.
    
    ## Next Steps
    
    - `/skill-smith` — to build approved skills
    
    > **Human output.** This skill's handler-facing output obeys the human-output
    > contract (`human-output/SKILL.md`).
    
    > **Next skills.** On completion, run the Next Skills protocol (`next-skills/SKILL.md`): surface the `next-skills` recommendations from front-matter for the caller to pick. Offer only — never auto-invoke.
    
    > **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.

No comments yet.

Reviews (0)

No reviews yet.