Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
oimiragieo avatar

Recommend Evolution

  • 53 installs
  • 36 repo stars
  • Updated July 14, 2026
  • oimiragieo/agent-studio

Helps with ai & agent building tasks.

About

recommend-evolution is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted development.

  • recommend-evolution
  • AI & Agent Building
  • AI-coding skill

Recommend Evolution by the numbers

  • 53 all-time installs (skills.sh)
  • Ranked #6,979 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
  • Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/oimiragieo/agent-studio --skill recommend-evolution

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs53
repo stars36
Last updatedJuly 14, 2026
Repositoryoimiragieo/agent-studio

What it does

Helps with ai & agent building tasks.

Files

SKILL.mdMarkdownGitHub ↗

Recommend Evolution

Overview

Recommend ecosystem evolution when repeated evidence indicates missing capability, and record the recommendation in a standard machine-readable format.

When to Use

  • Reflection identifies recurring delivery failures with the same root cause
  • Router/analysis signals no suitable agent or skill for recurring requests
  • Repeated integration gaps imply missing artifact type or policy
  • User explicitly requests a new capability path

Iron Laws

1. NEVER spawn evolution-orchestrator directly from this skill — this skill records recommendations only; execution decisions belong to the orchestrator and approval pipeline. 2. ALWAYS validate trigger type against defined thresholds before recording a recommendation — vague observations are not triggers; require concrete failure counts or routing misses. 3. NEVER create a new evolution request when artifact-integrator or skill-updater would address the gap — reserve evolution for net-new capabilities, not integration or update gaps. 4. ALWAYS append the recommendation to the JSONL queue AND include the required report block in the current output — dual recording ensures the recommendation is discoverable at both runtime and review time. 5. NEVER proceed with a recommendation without evidence — single failures are noise; trigger thresholds exist for a reason.

<identity> Evolution recommendation skill for reflection/planning agents. </identity>

<capabilities>

  • Trigger classification (repeated_error, no_agent, integration_gap, user_request, rubric_regression, stale_skill, other)
  • Recommendation-vs-integration decision branching
  • Dual recording mode: JSONL runtime queue + reflection report block

</capabilities>

Trigger Taxonomy Note

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.

<instructions> <execution_process>

Step 0: Validate Trigger Type

Use these thresholds:

  • repeated_error: same class of failure in 5+ tasks
  • rubric_regression: repeated score drop below threshold for same class of task
  • no_agent: recurring need with no valid routing match
  • integration_gap: existing artifact integration missing (prefer artifact-integrator)
  • user_request: explicit request for capability not available
  • stale_skill: audit pipeline reports verified artifact older than 6 months or invalid lastVerifiedAt

Step 1: Decide Recommendation Path

  • If gap is integration of existing artifact, prefer:

Skill({ skill: 'artifact-integrator' })

  • If gap is stale/underperforming existing skill, prefer:

Skill({ skill: 'skill-updater' })

  • If gap requires net-new capability/artifact, continue with evolution recommendation
  • If no artifact change needed, update memory only and exit

Step 2: Create Standard Recommendation Payload

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

Step 3: Record Recommendation

1. Append JSON line to: .claude/context/runtime/evolution-requests.jsonl 2. Add required report block:

## Evolution Recommendation

- Trigger: <trigger>
- Evidence: <evidence>
- Suggested Artifact Type: <type|null>
- Summary: <1-2 sentences>
- Queue Record: `.claude/context/runtime/evolution-requests.jsonl`

Step 3: Output

Return recommendation summary and what was recorded.

</execution_process> </instructions>

<examples> <usage_example> Example Invocations:

// 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> </examples>

Anti-Patterns

Anti-PatternWhy It FailsCorrect Approach
Spawning evolution-orchestrator directly from this skillViolates single-responsibility; bypasses approval and resource gatesRecord recommendation to JSONL queue only; let the orchestrator decide on execution
Recording an evolution request for an integration gap that already has artifactsCreates unnecessary new artifacts when an integration fix would sufficeCheck artifact-integrator path first; escalate only if gap requires net-new capability
Submitting a recommendation without trigger evidenceUninformed evolution wastes resources and pollutes the queue with noiseRequire concrete evidence: failure counts, routing miss logs, or explicit user request
Routing stale-skill triggers through this skill instead of skill-updaterWrong escalation path; creates evolution requests for work that belongs in an update cycleRoute stale_skill triggers directly to skill-updater; only escalate if the skill cannot be updated
Triggering evolution after a single failure instanceSingle failures are noise; premature evolution wastes build capacityApply defined thresholds: 5+ repeated errors, consistent routing misses across sessions

Memory Protocol (MANDATORY)

Before starting:

Read .claude/context/memory/learnings.md using Read or Node fs.readFileSync (cross-platform).

After completing:

  • Recommendation pattern -> .claude/context/memory/learnings.md
  • Ambiguous trigger logic -> .claude/context/memory/issues.md
  • Evolution policy decision -> .claude/context/memory/decisions.md
ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.

Related skills

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.