AGENT SKILL

station

End-of-session composition that chains retrospect → document → cleanup → wrap-up into one closeout pipeline. Use this to fully close a working session — capture learnings, sync docs, prune artifacts, then commit and open a PR — without forgetting a step. Side-effecting; honors each sub-skill's confirmation and approval gates. Run explicitly.

License 许可
MIT
最近更新
2026-06-23
Stars
★ 0
Forks
0

01 前言 Front Matter

name
station
description
End-of-session composition that chains retrospect → document → cleanup → wrap-up into one closeout pipeline. Use this to fully close a working session — capture learnings, sync docs, prune artifacts, then commit and open a PR — without forgetting a step. Side-effecting; honors each sub-skill's confirmation and approval gates. Run explicitly.
disable-model-invocation
true

03 SKILL.md 正文

station — Combined End-of-Session Workflow

Run the full closeout pipeline in order. Each phase reuses the corresponding standalone skill and respects its gates.

Usage: /station


Overview

# Phase Reuses Gate
1 Retrospect retrospect none (write to registry)
2 Document document secret scan before write
3 Cleanup cleanup user confirmation
4 Wrap-up wrap-up branch guard + approval

If any phase halts (secret found, on main branch, user declines), stop the pipeline there and report — do not silently skip ahead.


Pre-Flight: Security Scan

grep -rn -iE "(sk_|pk_|api[_-]?key|secret|password|token|[a-z]+://[^ ]*:[^ ]*@)" \
  README.md CLAUDE.md docs/ .claude/ \
  --include="*.md" 2>/dev/null

If secrets found: STOP, alert the user, remove before continuing.


Phase 1: Retrospect

Mine the session, classify insights (K-PAT / K-PIT / K-ARC / K-PRF / K-SEC), append entries to .claude/knowledge/REGISTRY.md using the Context → Learning → Application → Metric schema. (See the retrospect skill.)

Phase 2: Document

Scan the code, secret-scan the docs, then apply targeted edits to STATUS.md / CLAUDE.md / README so they match reality. (See the document skill.)

Phase 3: Cleanup

Audit git branches, stale session files, and temp caches. Present the report table and wait for confirmation before deleting anything. Never touch main/current branch, env, secrets, or databases. (See the cleanup skill.)

Phase 4: Wrap-up

Update STATUS, confirm you are on a feature branch, security-grep the diff, make a conventional commit (no AI-tool mentions), get approval, then push and open a PR. (See the wrap-up skill.)


Output

SESSION STATION COMPLETE
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
RETROSPECT  knowledge entries: N
DOCUMENT    files updated: [list]    alignment: [clean | N issues]
CLEANUP     branches pruned: N       artifacts cleared: [size]
WRAP-UP     commit: [hash]           PR: [url]

Session closed.

Safety Rules

  1. Secret scan before any doc write.
  2. Cleanup requires explicit confirmation.
  3. Wrap-up requires a feature branch and explicit approval before push.
  4. Code is truth; docs describe what IS.
  5. Never commit secrets; never push to main.
  6. Halt the chain on the first gate that fails — report, don't skip.

04 同仓库更多 Skills

Elad73
Elad73/agentic-base-layer

wrap-up

Session-end safe closeout. Updates STATUS, verifies you are on a feature branch (never main), security-greps the diff for secrets, makes a conventional commit (no AI-tool mentions), then asks for approval before pushing and opening a PR. Use this to properly close a development session. Side-effecting and gated on explicit user approval; run explicitly.

★ 0
Elad73
Elad73/agentic-base-layer

wake-up

Session-start context sync. Reads project STATUS, git state, and runs a quick health check, then emits a short (<15 line) announcement of where things stand and the single best next step. Use this at the beginning of a working session to re-establish context fast. Does NOT re-read CLAUDE.md (already in the system prompt). Read-only and fast.

★ 0
Elad73
Elad73/agentic-base-layer

retrospect

Post-session learning capture. Mines the current conversation for reusable patterns, pitfalls, architecture decisions, performance and security insights, then appends them to the project knowledge registry. Use this at the end of a working session, after a bug is fixed, or after a non-obvious decision is made — so the next session starts smarter. Writes structured entries to .claude/knowledge/REGISTRY.md.

★ 0
Elad73
Elad73/agentic-base-layer

pre-ship

Mandatory pre-commit quality gates — type-check, lint, test, build — run in order and halting on the first failure. Use this BEFORE committing any change that touches application code, so failures are caught while context is still fresh instead of by CI. Surfaces the failing tool's verbatim error and refuses to proceed until gates pass.

★ 0
Elad73
Elad73/agentic-base-layer

document

Code-is-truth documentation sync. Detects drift between the codebase and project docs (STATUS.md, CLAUDE.md, README), then applies targeted edits so docs describe what the code actually is. Use this after shipping features, before a release, or when docs feel stale. Secret-scans every doc before writing. Makes small surgical edits, never wholesale rewrites.

★ 0
Elad73
Elad73/agentic-base-layer

debug-like-expert

Deep analysis debugging mode for complex issues. Activates methodical investigation protocol with evidence gathering, hypothesis testing, and rigorous verification. Use when standard troubleshooting fails or when issues require systematic root cause analysis.

★ 0