CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-05-01 19:25:10 +02:00
Code Issues Packages Projects Releases Wiki Activity

feat: add trigger phrases to skill descriptions for better model matching (v0.6.4.1) (#169)

Browse Source 
* feat: add trigger phrases to skill descriptions for better model matching

Anthropic's skill best practices: "the description field is not a summary —
it's when to trigger." Add explicit "Use when asked to..." phrases to 12 skill
descriptions so Claude's auto-discovery works with natural language requests
like "deploy this" or "check my diff", not just explicit /slash-commands.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* docs: add on-demand hooks and telemetry to TODOS.md

Captures two ideas from Anthropic's skill best practices post:
- /careful, /freeze, /guard on-demand hook skills (P3)
- Skill usage telemetry via preamble JSONL append (P3)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: bump version and changelog (v0.6.4.1)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* docs: exclude internal details from CHANGELOG style guide

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-03-18 08:06:46 -05:00
committed by GitHub
parent 716e4c934a
commit bc86a665b7
28 changed files with 80 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
TODOS.md
+31
View File
@@ -482,6 +482,37 @@ Shipped as `/design-consultation` on garrytan/design branch. Renamed from `/setu
**Priority:** P3
**Depends on:** Boil the Lake shipped (v0.6.1)
## Safety & Observability
### On-demand hook skills (/careful, /freeze, /guard)
**What:** Three new skills that use Claude Code's session-scoped PreToolUse hooks to add safety guardrails on demand.
**Why:** Anthropic's internal skill best practices recommend on-demand hooks for safety. Claude Code already handles destructive command permissions, but these add an explicit opt-in layer for high-risk sessions (touching prod, debugging live systems).
**Skills:**
- `/careful` — PreToolUse hook on Bash tool. Warns (not blocks) before destructive commands: `rm -rf`, `DROP TABLE`, `git push --force`, `git reset --hard`, `kubectl delete`, `docker system prune`. Uses `permissionDecision: "ask"` so user can override.
- `/freeze` — PreToolUse hook on Edit/Write tools. Restricts file edits to a user-specified directory. Great for debugging without accidentally "fixing" unrelated code.
- `/guard` — meta-skill composing `/careful` + `/freeze` into one command.
**Implementation notes:** Use `${CLAUDE_SKILL_DIR}` (not `${SKILL_DIR}`) for script paths in hook commands. Pure bash JSON parsing (no jq dependency). Freeze dir storage: `${CLAUDE_PLUGIN_DATA}/freeze-dir.txt` with `~/.gstack/freeze-dir.txt` fallback. Ensure trailing `/` on freeze dir paths to prevent `/src` matching `/src-old`.
**Effort:** M (human) / S (CC)
**Priority:** P3
**Depends on:** None
### Skill usage telemetry
**What:** Track which skills get invoked, how often, from which repo.
**Why:** Enables finding undertriggering skills and measuring adoption. Anthropic uses a PreToolUse hook for this; simpler approach is appending JSONL from the preamble.
**Context:** Add to `generatePreamble()` in `scripts/gen-skill-docs.ts`. Append to `~/.gstack/analytics/skill-usage.jsonl` with skill name, timestamp, and repo name. `mkdir -p` ensures the directory exists.
**Effort:** S (human) / S (CC)
**Priority:** P3
**Depends on:** None
## Completed
### Phase 1: Foundations (v0.2.0)