Menu
Detect capability gaps and record standardized evolution recommendations.
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/oimiragieo/agent-studio --skill recommend-evolutionThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Based on SOC occupation classification
Showing SKILL.md
| name | recommend-evolution |
| description | Detect capability gaps and record standardized evolution recommendations. |
| version | 1.1.0 |
| model | sonnet |
| invoked_by | both |
| user_invocable | true |
| tools | ["Read","Write","Edit","Skill"] |
| error_handling | graceful |
| streaming | supported |
| verified | true |
| lastVerifiedAt | "2026-02-22T00:00:00.000Z" |
| source | builtin |
| trust_score | 100 |
| provenance_sha | 8865ccfce5be1e54 |
Recommend ecosystem evolution when repeated evidence indicates missing capability, and record the recommendation in a standard machine-readable format.
recommend-evolution uses a cause-oriented trigger taxonomy (repeated_error, no_agent, integration_gap, user_request, rubric_regression, stale_skill, other).
This intentionally differs from skill-updater, which uses a caller-oriented trigger taxonomy (reflection, evolve, manual, stale_skill) to describe who/what initiated the update path.
Use these thresholds:
repeated_error: same class of failure in 5+ tasksrubric_regression: repeated score drop below threshold for same class of taskno_agent: recurring need with no valid routing matchintegration_gap: existing artifact integration missing (prefer artifact-integrator)user_request: explicit request for capability not availablestale_skill: audit pipeline reports verified artifact older than 6 months or invalid lastVerifiedAtSkill({ skill: 'artifact-integrator' })Skill({ skill: 'skill-updater' })Build one JSON object with required fields:
{
"timestamp": "2026-02-14T00:00:00.000Z",
"source": "reflection-agent",
"trigger": "repeated_error",
"evidence": "Same routing failure observed in 6 tasks over 2 days.",
"suggestedArtifactType": "skill",
"summary": "Create a new routing-context skill for reflection-time grounding.",
"status": "proposed"
}
Schema reference:
.claude/schemas/evolution-request.schema.json
.claude/context/runtime/evolution-requests.jsonl## Evolution Recommendation
- Trigger: <trigger>
- Evidence: <evidence>
- Suggested Artifact Type: <type|null>
- Summary: <1-2 sentences>
- Queue Record: `.claude/context/runtime/evolution-requests.jsonl`
Return recommendation summary and what was recorded.
</execution_process>
// Repeated failure pattern -> recommend skill creation
Skill({
skill: 'recommend-evolution',
args: '--trigger repeated_error --suggestedArtifactType skill',
});
// Routing miss -> recommend new agent/workflow discussion
Skill({ skill: 'recommend-evolution', args: '--trigger no_agent --suggestedArtifactType agent' });
</usage_example>
| Anti-Pattern | Why It Fails | Correct Approach |
|---|---|---|
| Spawning evolution-orchestrator directly from this skill | Violates single-responsibility; bypasses approval and resource gates | Record recommendation to JSONL queue only; let the orchestrator decide on execution |
| Recording an evolution request for an integration gap that already has artifacts | Creates unnecessary new artifacts when an integration fix would suffice | Check artifact-integrator path first; escalate only if gap requires net-new capability |
| Submitting a recommendation without trigger evidence | Uninformed evolution wastes resources and pollutes the queue with noise | Require concrete evidence: failure counts, routing miss logs, or explicit user request |
| Routing stale-skill triggers through this skill instead of skill-updater | Wrong escalation path; creates evolution requests for work that belongs in an update cycle | Route stale_skill triggers directly to skill-updater; only escalate if the skill cannot be updated |
| Triggering evolution after a single failure instance | Single failures are noise; premature evolution wastes build capacity | Apply defined thresholds: 5+ repeated errors, consistent routing misses across sessions |
Before starting:
Read .claude/context/memory/learnings.md using Read or Node fs.readFileSync (cross-platform).
After completing:
.claude/context/memory/learnings.md.claude/context/memory/issues.md.claude/context/memory/decisions.mdASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.
Agent frontmatter enhancements — disallowedTools, mcpServers scoping, fork_eligible field
Context management — pre-compact persistence, threshold alignment, microcompact/circuit breaker detection
Hook enhancements — updatedInput for bash safety prefixes, suppressOutput for verbose blocks, denial-based routing feedback