feature-radar/feature-radar-archive/SKILL.md
Archive a completed, rejected, or covered feature into .feature-radar/archive/ with mandatory learning extraction. MUST use this skill whenever a feature reaches a terminal state — done, rejected, covered, deferred, or N/A. Even casual mentions like "we shipped X" or "X is done" should trigger this. The skill extracts learnings, derives new opportunities, and updates refs. Use when the user: - Says "we shipped X", "X is done", "X is complete", "we just finished X" - Rejects a feature: "we decided not to build X", "reject this", "doesn't fit" - Defers: "defer X", "postpone this", "revisit later", "not now" - Closes an opportunity: "close this opportunity", "mark as done", "archive this" - Mentions any feature reaching Done/Covered/Rejected/Deferred status Do NOT use for discovering new features — that's feature-radar-scan's job.
npx skillsauth add runkids/my-skills feature-radar-archiveInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Move a feature to .feature-radar/archive/ and run the mandatory extraction checklist.
Identify the feature — ask the user which feature to archive. Check opportunities/ for an existing file to move.
Determine status:
Create archive file — write .feature-radar/archive/{nn}-{slug}.md
Checkpoint — Review & Annotate per ../feature-radar/references/WORKFLOW-PATTERNS.md
Run extraction checklist:
□ archive/{nn}-{slug}.md created with correct status □ Extract learnings → specs/{topic}.md □ Derive new opportunities → opportunities/{nn}-{slug}.md □ Update references → references/{topic}.md □ Update ecosystem trends → specs/ecosystem-trends.md
Acceptable responses per check:
opportunities/ file, delete itCheckpoint: Present extraction results using this format:
Archive: {nn}-{slug} ({status})
| Check | Result |
|-------|--------|
| Learnings | {created specs/X.md / updated specs/X.md / none} |
| Opportunities | {created opportunities/X.md / none} |
| References | {updated references/X.md / none} |
| Ecosystem | {updated specs/ecosystem-trends.md / none} |
Use the format defined in ../feature-radar/references/SPEC.md § 3.2 (archive/{nn}-{slug}.md).
opportunities/, use the same number. If it's new, use the next available number.→ Moved opportunities/04-config-merge.md → archive/04-config-merge.md (Done)
→ Learnings: specs/yaml-config-merge.md (new)
→ New opportunity: opportunities/09-config-validation.md
→ References: no updates | Ecosystem: no changes
→ Updated base.md: archive 3→4, specs 2→3
Follow the template in ../feature-radar/references/DIRECTIVES.md, with skill name "Archive Complete".
tools
Manages and syncs AI CLI skills and agents across 50+ tools from a single source. Use this skill whenever the user mentions "skillshare", runs skillshare commands, manages skills or agents (install, update, uninstall, sync, audit, analyze, check, diff, search), or troubleshoots skill/agent configuration (orphaned symlinks, broken targets, sync issues). Covers both global (~/.config/skillshare/) and project (.skillshare/) modes. Also use when: adding new AI tool targets (Claude, Cursor, Windsurf, etc.), setting target include/exclude filters or copy vs symlink mode, using backup/restore or trash recovery, piping skillshare output to scripts (--json), setting up CI/CD audit pipelines, building/sharing skill hubs (hub index, hub add), or working with agents (single .md files synced to agent-capable targets like Claude, Cursor, Augment, OpenCode) via positional `agents` filter or `--kind agent`, plus `.agentignore` and `enable`/`disable` for per-agent toggles.
development
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
testing
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
development
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.