skill-forge

A draft-maker for turning a difficult, repeatable solution into a reusable coding-agent skill. It checks whether the solution is reproducible, likely to recur, and not already covered.

In plain words
What is it for?
Use it after solving a non-trivial problem to assess the solution and write a skill draft. In its supported project, it can also prepare the files and synchronization steps after approval.
Why use it?
It prevents useful procedures from disappearing when a work session ends. It also avoids creating unnecessary skills when a note or improvement to an existing skill is enough.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/this-hw/claude-code-kit/skill-forge
Any agent
npx skills add This-HW/claude-code-kit --skill skill-forge
Clone the repo
git clone --depth 1 https://github.com/This-HW/claude-code-kit

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,425 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00051 $0.01425
Opus 5 $0.00026 $0.00713
Sonnet 5 $0.00010 $0.00285
Haiku 4.5 $0.00005 $0.00143

Measured yesterday against content hash 6f52ca78c7f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-forge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/common/skills/skill-forge/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Forge — 성공 경험을 재사용 자산으로

kit의 학습 루프는 비대칭이다. 실패는 ledger → LESSONS → /self-improve로 흐르는데, 성공은 아무 데도 안 남는다. 어려운 문제를 푼 세션의 절차 지식이 세션 종료와 함께 소멸하고, 다음에 같은 문제를 만나면 처음부터 다시 푼다.

이 스킬은 그 절반을 메운다 — 단, 아무 성공이나 스킬이 되지는 않는다.

적용 범위: 승인 후 적용 단계(스킬 파일 생성 + 3표면 동기화 + 카운트/버전 게이트)는 kit 레포 자체의 개발을 전제한다. 소비자 프로젝트에서는 3조건 판정과 초안 작성까지가 유효하며, 산출한 초안은 그 프로젝트의 .claude/skills/에 사용자가 직접 배치한다.

포징 임계 (3조건 — AND)

조건 판정 질문 미충족 시 강등 경로
재현성 이 절차를 그 세션의 맥락 없이 그대로 다시 실행할 수 있는가? ./scripts/feedback.sh upsert로 ledger 한 줄
반복성 앞으로 다시 마주칠 문제인가? (1회성 마이그레이션·특정 사고 대응은 아니다) Work 문서(progress.md/decisions.md)에 기록
비중복 기존 스킬로 커버되지 않는가? 기존 스킬 보강 제안으로 전환 (새 스킬 만들지 않음)

세 번째 조건이 가장 자주 걸린다. "새 스킬이 있으면 편하겠다"는 거의 항상 "기존 스킬에 한 절이 빠져 있다"의 오독이다. 스킬 개수는 자산이 아니라 비용이다 — 트리거 맵이 커질수록 어느 것도 안 걸린다.

절차

1. 후보 서술 [건너뛰기 금지]

무엇을 풀었는지가 아니라 **"다음 사람이 같은 상황에서 무엇을 해야 하는가"**로 쓴다. 전자는 회고이고 후자만 스킬이다.

2. 3조건 판정 [건너뛰기 금지]

각 조건에 근거와 함께 판정을 적는다. "그럴 것 같다"는 판정이 아니다.

비중복 판정은 실제 목록과 대조한다:

ls plugins/common/skills/                       # kit 스킬
ls ~/.claude/plugins/*/*/skills/ 2>/dev/null    # 설치된 다른 플러그인 (없으면 건너뛴다)

다른 플러그인의 존재를 가정하지 않는다. superpowers 등이 설치돼 있으면 그 목록과도 대조하고, 없으면 그 단계를 조용히 건너뛴다 (fail-open). 특정 플러그인이 있어야만 동작하는 절차는 consumer-first 위반이다.

미충족이면 여기서 멈추고 강등 경로를 실행한 뒤 보고한다.

3. 초안 작성 (파일로 남기지 않는다)

/skill-creator의 템플릿 규약을 따른다:

  • frontmatter: name(kebab-case, 파일 경로와 일치) · description(영문, 트리거 조건 포함) · model · effort
  • 본문: 사용 시점 표 → 절차(각 단계에 [건너뛰기 금지] 여부 명시) → 실패 모드 → delegation signal
  • 정직한 한계 절을 반드시 넣는다 — 이 스킬이 보장하지 않는 것.

4. 사용자 승인 대기 [건너뛰기 금지]

초안 전문과 3조건 판정 근거를 함께 제시하고 승인을 받는다. 승인 없는 상태에서 다음 단계로 넘어가지 않는다.

Read the full file on GitHub · 101 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 101 lines · 51 tokens per session scan A 6f52ca78c7f2

Subscribe to this mod's changes

skill-forge is a skill published in the GitHub repository This-HW/claude-code-kit (4 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 1,425 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

watch

File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…

SethGammon/Citadel · 70 tokens

pr-watch

Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.

SethGammon/Citadel · 46 tokens

qa

Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).

SethGammon/Citadel · 56 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

live-preview

Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.

SethGammon/Citadel · 40 tokens

wiki

Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.

SethGammon/Citadel · 56 tokens