docs(skills): mark cwd-skill discovery verified in headless mode
This commit is contained in:
@@ -155,14 +155,10 @@ New `SessionSkillDto`.
|
|||||||
## Verification (must-check, can't be unit-tested)
|
## Verification (must-check, can't be unit-tested)
|
||||||
|
|
||||||
- **Does `claude -p` actually load and invoke a skill placed in cwd `.claude/skills/`?**
|
- **Does `claude -p` actually load and invoke a skill placed in cwd `.claude/skills/`?**
|
||||||
Load-bearing assumption. Smoke test 2026-07-03: `system:init` confirms correct `cwd` +
|
**CONFIRMED 2026-07-03.** Mika ran, in a stable terminal, a `claude -p` invocation in a
|
||||||
`Skill` tool present; one authed run engaged the ponytail skill (12 mentions, vs zero on
|
scratch cwd holding `.claude/skills/ponytail*/SKILL.md`; the model invoked the
|
||||||
an unauthed run). **Clean repro is blocked by auth-token rotation in the bash sandbox**
|
`ponytail-help` skill and returned its exact Lite/Full/Ultra table. Headless mode does
|
||||||
(parallel-session contention, not a design issue) — Mika confirms with one run in a
|
surface cwd skills → the whole approach holds; no `CLAUDE_CONFIG_DIR` fallback needed.
|
||||||
stable terminal:
|
|
||||||
`cd /tmp/claudedo-skill-smoke && echo "Use the ponytail-help skill to show the levels table, then stop." | claude -p --permission-mode acceptEdits --max-turns 4`.
|
|
||||||
If headless does *not* surface cwd skills, fall back to `CLAUDE_CONFIG_DIR` isolation
|
|
||||||
(heavier — needs credentials copied) and revisit.
|
|
||||||
- Seeded skill is **not** committed by the auto-commit step (worktree run).
|
- Seeded skill is **not** committed by the auto-commit step (worktree run).
|
||||||
- Skill does not appear in a normal interactive session (no global leak).
|
- Skill does not appear in a normal interactive session (no global leak).
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user