How this skill is triggered — by the user, by Claude, or both
Slash command
/spec:applyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Implement the plan from a spec change.
Implement the plan from a spec change.
Input: Optionally specify a change name (e.g., /spec:apply add-auth). If
omitted, check if it can be inferred from conversation context. If vague or
ambiguous you MUST prompt for available changes.
Steps
Select the change
If a name is provided, use it. Otherwise:
specs/changes/specs/changes/ (excluding archive/)
and use the AskUserQuestion tool to let the user selectAlways announce: "Using change: " and how to override (e.g.,
/spec:apply <other>).
Read context artifacts
Read the change's artifacts from specs/changes/<name>/:
proposal.md — what and whydomain.md — domain concepts (if present)architecture.md — technical approachplan.md — implementation stepsIf plan.md is missing: show message, suggest using /spec:propose first.
Show current progress
Parse plan.md and count - [ ] (pending) vs - [x] (complete).
Display:
If all steps are already complete: congratulate, suggest /spec:archive.
Implement steps (loop until done or blocked)
For each pending step:
- [ ] → - [x]Pause if:
On completion or pause, show status
Display:
Output During Implementation
## Implementing: <change-name>
Working on step 3/7: <step description>
[...implementation happening...]
✓ Step complete
Working on step 4/7: <step description>
[...implementation happening...]
✓ Step complete
Output On Completion
## Implementation Complete
**Change:** <change-name>
**Progress:** 7/7 steps complete ✓
### Completed This Session
- [x] Step 1
- [x] Step 2
...
All steps complete! You can archive this change with `/spec:archive`.
Output On Pause (Issue Encountered)
## Implementation Paused
**Change:** <change-name>
**Progress:** 4/7 steps complete
### Issue Encountered
<description of the issue>
**Options:**
1. <option 1>
2. <option 2>
3. Other approach
What would you like to do?
Guardrails
Fluid Workflow Integration
This skill supports the "actions on a change" model:
npx claudepluginhub tillg/till-claude-code-marketplace --plugin specGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.