Agent skill

Retrospective Agent

by Ibrahim-3d in Ibrahim-3d/orchestrator-supaconductor

Runs after every track completion to extract learnings. An agent skill from Ibrahim-3d/orchestrator-supaconductor.

AGPL-3.0Auto-check passedProduct & Project Management

Install Retrospective Agent

skills CLI
$ npx skills add Ibrahim-3d/orchestrator-supaconductor --skill retrospective-agent -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Ibrahim-3d/orchestrator-supaconductor retrospective-agent --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Ibrahim-3d/orchestrator-supaconductor.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/knowledge/retrospective-agent .claude/skills/retrospective-agent && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
retrospective-agent
GitHub stars
381
Token cost
~1.9k tokens
SKILL.md length
368 words
Files
1
Skills in repo
27
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Runs after every track completion to extract learnings. An agent skill from Ibrahim-3d/orchestrator-supaconductor.

  • Works in 6 steps: Analyze Track Execution → Extract Patterns → Extract Error Patterns → …
  • Tasks that involve Retrospectives
  • SKILL.md covers When This Runs, Inputs, Workflow and Output Format, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Retrospective Agent is an agent skill from Ibrahim-3d/orchestrator-supaconductor. Runs after every track completion to extract learnings. Analyzes what worked, what failed, and what patterns emerged. Updates conductor/knowledge/patterns.md with new solutions and errors.json with new error patterns. Proposes skill updates if workflow improvements are identified. Triggered automatically by orchestrator after COMPLETE step.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Product & Project Management, covering Retrospectives. The repository describes itself as: Multi-agent orchestration system for Claude Code with parallel execution, automated quality gates, Board of Directors, and bundled Superpowers skills. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Retrospectives

Example prompts

  • “/retrospective-agent”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Analyze Track Execution
  2. Extract Patterns
  3. Extract Error Patterns
  4. Identify Skill Improvements
  5. Update Knowledge Base
  6. Create Track Retrospective

What it can do on your machine

Read from SKILL.md and the folder at commit 76c9b10. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown, json and typescript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Retrospective Agent loads about 1.9k tokens when it runs. Until then it costs about 91 tokens; SKILL.md has 368 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~91
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Ibrahim-3d/orchestrator-supaconductor at commit 76c9b10, republished under its AGPL-3.0 licence (© Ibrahim-3d). 368 words, ~1,906 tokens.

Download SKILL.mdSave it as .claude/skills/retrospective-agent/SKILL.md (or your agent's skills folder).
name
retrospective-agent
description
Runs after every track completion to extract learnings. Analyzes what worked, what failed, and what patterns emerged. Updates conductor/knowledge/patterns.md with new solutions and errors.json with new error patterns. Proposes skill updates if workflow improvements are identified. Triggered automatically by orchestrator after COMPLETE step.

Retrospective Agent — Post-Track Learning

Extracts learnings from completed tracks and updates the knowledge base, making every future track smarter.

When This Runs

Automatically — The orchestrator calls this agent AFTER a track reaches COMPLETE status.

Inputs

  1. Track's plan.md — All tasks, including fix cycles
  2. Track's metadata.json — Fix cycle count, lead consultations, blockers
  3. Track's commits — What was actually built
  4. Track's spec.md — Original requirements (to measure alignment)

Workflow

1. Analyze Track Execution

Review the track's execution data:

markdown
## Track Analysis: [track-id]

### Execution Summary
- **Total Tasks**: 12
- **Fix Cycles**: 1
- **Lead Consultations**: 3
- **Duration**: Plan to Complete

### What Worked Well
- [Extracted from smooth tasks with no fix cycles]

### What Caused Problems
- [Extracted from fix cycles and blocked tasks]

### Patterns Discovered
- [New solutions that could be reused]

### Errors Encountered
- [New error patterns and their fixes]
2. Extract Patterns

Look for reusable solutions in the completed work:

Pattern Candidates:

  • Solutions that required multiple iterations to get right
  • Code structures that were repeated across tasks
  • Approaches that prevented anticipated problems
  • Integrations that worked particularly well

Pattern Template:

markdown
### [Pattern Name]
**Category**: [UI | State | API | Auth | Integration | Testing | Performance]
**Discovered**: [track-id] on [date]
**Problem**: What problem does this solve?
**Solution**: How to implement it
**Code Example**: (key code snippet)
**Gotchas**: Watch out for...
3. Extract Error Patterns

Look for errors that were fixed during the track:

Error Candidates:

  • Errors that appeared in fix cycles
  • Errors that blocked progress
  • Errors with non-obvious solutions
  • Errors likely to recur in similar work

Error Template:

json
{
  "id": "err-XXX",
  "pattern": "Regex pattern matching the error",
  "category": "typescript|react|nextjs|supabase|stripe|etc",
  "context": "When this error typically occurs",
  "problem": "What causes this error",
  "solution": "How to fix it",
  "code_fix": "Code snippet if applicable",
  "occurrences": 1,
  "last_seen": "2026-01-31",
  "discovered_in": "track-id"
}
4. Identify Skill Improvements

Check if the track revealed workflow issues:

Questions to Ask:

  • Did any step take longer than expected? Why?
  • Were there repeated back-and-forth fix cycles?
  • Did evaluators miss issues that appeared later?
  • Were lead consultations helpful or did they escalate unnecessarily?
  • Did the plan have gaps the executor discovered?

Improvement Candidates:

  • Evaluator checklist additions
  • Planner prompt enhancements
  • New lead authority grants
  • Workflow step modifications
Show full SKILL.md (146 more words)Show less
5. Update Knowledge Base
Update patterns.md

Append new patterns to the appropriate category section:

markdown
## [Category] Patterns

### [New Pattern Name]
**Category**: [Category]
**Discovered**: [track-id] on [YYYY-MM-DD]
**Problem**: [Problem statement]
**Solution**: [Solution description]
**Code Example**:
```[language]
[code]

Gotchas: [Warnings]


#### Update errors.json

Add new error patterns:

```typescript
// read_file current errors.json
const errors = JSON.parse(await readFile('conductor/knowledge/errors.json'));

// Add new error
errors.errors.push({
  id: `err-${String(errors.errors.length + 1).padStart(3, '0')}`,
  pattern: "New error pattern regex",
  category: "category",
  context: "When this occurs",
  problem: "What causes it",
  solution: "How to fix",
  code_fix: "Code if applicable",
  occurrences: 1,
  last_seen: new Date().toISOString().split('T')[0],
  discovered_in: trackId
});

// write_file back
await writeFile('conductor/knowledge/errors.json', JSON.stringify(errors, null, 2));
6. Create Track Retrospective

write_file a retrospective file for the track:

Location: conductor/tracks/[track-id]/retrospective.md

markdown
# Retrospective: [Track ID]

**Completed**: [YYYY-MM-DD]
**Duration**: [X days/hours]
**Fix Cycles**: [N]

## Summary

[1-2 sentence summary of what the track accomplished]

## What Worked Well

- [Thing 1]
- [Thing 2]

## What Caused Problems

- [Problem 1]: [How it was resolved]
- [Problem 2]: [How it was resolved]

## Patterns Extracted

- **[Pattern Name]** → Added to patterns.md under [Category]

## Errors Logged

- **[Error Pattern]** → Added to errors.json as err-XXX

## Skill Improvements Proposed

- [ ] [Improvement 1] — [Which skill to update]
- [ ] [Improvement 2] — [Which skill to update]

## Recommendations for Similar Tracks

- [Advice for future tracks doing similar work]

Output Format

The Retrospective Agent returns:

json
{
  "track_id": "feature-name_20260131",
  "completed_at": "2026-01-31T15:00:00Z",

  "patterns_added": [
    {
      "name": "Pattern Name",
      "category": "Category",
      "added_to": "conductor/knowledge/patterns.md"
    }
  ],

  "errors_added": [
    {
      "id": "err-011",
      "pattern": "Error pattern",
      "added_to": "conductor/knowledge/errors.json"
    }
  ],

  "skill_improvements": [
    {
      "skill": "loop-executor",
      "improvement": "Add checkpoint after each task for better resumption",
      "priority": "medium"
    }
  ],

  "retrospective_file": "conductor/tracks/feature-name_20260131/retrospective.md"
}

Integration with Orchestrator

The orchestrator triggers retrospective after completion:

typescript
// In conductor-orchestrator, after track reaches COMPLETE
async function runRetrospective(trackId: string) {
  const result = await Task({
    subagent_type: "general-purpose",
    description: "Run track retrospective",
    prompt: `You are the retrospective-agent.

      Track: ${trackId}

      1. read_file conductor/tracks/${trackId}/plan.md
      2. read_file conductor/tracks/${trackId}/metadata.json
      3. Analyze what worked and what failed
      4. Extract patterns → Update conductor/knowledge/patterns.md
      5. Extract errors → Update conductor/knowledge/errors.json
      6. write_file retrospective to conductor/tracks/${trackId}/retrospective.md

      Return summary of learnings added.`
  });

  console.log(`Retrospective complete. ${result.patterns_added.length} patterns, ${result.errors_added.length} errors added.`);
}

Skip Conditions

Skip retrospective if:

  • Track had 0 fix cycles AND 0 lead consultations (nothing notable to learn)
  • Track was trivial (< 3 tasks)
  • Track was documentation-only

Learning Priorities

Prioritize extracting learnings about:

  1. High-value patterns — Solutions that took multiple attempts to get right
  2. Recurring errors — Errors similar to ones we've seen before
  3. Process friction — Steps that caused unnecessary delay
  4. Lead decisions — Whether lead consultations were helpful

Continuous Improvement

Over time, the knowledge base grows:

  • More patterns → Faster planning (reuse solutions)
  • More errors → Faster fixing (known solutions)
  • Skill improvements → Better workflows

The goal: Every track makes the next track easier.

© Ibrahim-3d, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/knowledge/retrospective-agent of Ibrahim-3d/orchestrator-supaconductor.

Open the folder on GitHubat commit 76c9b10

Compare with similar skills

Retrospective Agent next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Retrospective Agent compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Retrospective Agent this skillIbrahim-3d/orchestrator-supaconductor381—~1.9kAutomated safety check: PassAGPL-3.0
Weekly Engineering Retrogarrytan/gstack136k—~2.4kAutomated safety check: PassMIT
Dough Execute Planterryyin/lizard2.6k—~4.3kAutomated safety check: PassCustom licence
Oral Paper SkillAdkid-Zephyr/oral-paper-skill350—~1.9kAutomated safety check: PassNone
Deck Retroasheshgoplani/agent-deck1k—~1.8kAutomated safety check: PassMIT
Dough Execution Retrospectiveterryyin/lizard2.6k—~4kAutomated safety check: PassCustom licence

Similar skills

  • Builds a weekly engineering retrospective from git history: commit counts, per-person contributions, work patterns and code quality numbers over a chosen window.

    136k GitHub stars~2.4k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Dough Execute Plan

    terryyin/lizard

    Executes one selected story or bounded retrospective correction through an executable plan, or one authorized planless slice from a selected simple story or a contextual instruction, with…

    2.6k GitHub stars~4.3k tokensUpdated 3 days ago
    Product & Project ManagementAuto-check passed
  • Oral Paper Skill

    Adkid-Zephyr/oral-paper-skill

    Help authors learn from exemplary ICLR, ICML, and NeurIPS papers through source-linked manuscript comparisons, concrete writing and experiment suggestions, and guided reflection.

    350 GitHub stars~1.9k tokensUpdated 22 days ago
    Product & Project ManagementAuto-check passed
  • Deck Retro

    asheshgoplani/agent-deck

    Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs.

    1k GitHub stars~1.8k tokensUpdated 4 days ago
    Product & Project ManagementAuto-check passed
  • Reviews planned, completed planless quick, or quick-to-planned execution against original intent, aggregate commits, current whole-product architecture, and tests, including after cleanup.

    2.6k GitHub stars~4k tokensUpdated 3 days ago
    Product & Project ManagementAuto-check passed
  • Criticism Self Criticism

    HughYau/qiushi-skill

    批评与自我批评:在工作完成、阶段验收、收到批评或同类错误反复出现时,对成果和过程做诚实、具体、基于事实的审视,输出可执行的改进项,并处理外来批评而不辩解。触发信号包括 review、复盘、审查、"帮我看看有没有问题"、"你确定吗";任务刚开始或只是单步查询时不触发。

    3.8k GitHub stars~423 tokensUpdated 8 days ago
    Product & Project ManagementAuto-check passed

More from Ibrahim-3d/orchestrator-supaconductor

All 27 skills in this repo
  • Cto Advisor

    Ibrahim-3d/orchestrator-supaconductor

    Technical leadership guidance for engineering teams, architecture decisions, and technology strategy.

    381 GitHub starsUsed in 4 repos~2.4k tokens
    Auto-check passed
  • Context Driven Development

    Ibrahim-3d/orchestrator-supaconductor

    A skill your agent uses when working with Conductor's context-driven development methodology, managing project context artifacts, or understanding the relationship between product.md, tech-stack.md…

    381 GitHub starsUsed in 9 repos~2.9k tokens
    Auto-check passed
  • Agent Factory

    Ibrahim-3d/orchestrator-supaconductor

    Creates specialized worker agents dynamically from templates.

    381 GitHub stars~2.9k tokensUpdated 12 days ago
    Auto-check passed
  • Board Of Directors

    Ibrahim-3d/orchestrator-supaconductor

    Simulate a 5-member expert board deliberation for major decisions.

    381 GitHub stars~1.9k tokensUpdated 12 days ago
    Auto-check passed
  • Business Docs Sync

    Ibrahim-3d/orchestrator-supaconductor

    A skill your agent uses when completing a track that changes pricing, AI models, product features, or asset pipelines — syncs business context documents across all tiers.

    381 GitHub stars~2.1k tokensUpdated 12 days ago
    Auto-check passed
  • Context Loader

    Ibrahim-3d/orchestrator-supaconductor

    Load project context efficiently for Conductor workflows. An agent skill from Ibrahim-3d/orchestrator-supaconductor.

    381 GitHub stars~830 tokensUpdated 12 days ago
    Auto-check passed

Questions about Retrospective Agent

What does Retrospective Agent do?

Runs after every track completion to extract learnings. An agent skill from Ibrahim-3d/orchestrator-supaconductor. Retrospective Agent is an agent skill from Ibrahim-3d/orchestrator-supaconductor. Runs after every track completion to extract learnings.

When should I use Retrospective Agent?

Retrospective Agent fits situations like: tasks that involve Retrospectives.

How do I install Retrospective Agent in Claude Code?

Run `npx skills add Ibrahim-3d/orchestrator-supaconductor --skill retrospective-agent -a claude-code`. Or copy the skill folder (skills/knowledge/retrospective-agent in Ibrahim-3d/orchestrator-supaconductor) into .claude/skills/retrospective-agent in your project. Claude Code loads it when a task matches its description.

How do I install Retrospective Agent in Codex?

Run `npx skills add Ibrahim-3d/orchestrator-supaconductor --skill retrospective-agent -a codex`. Or copy the skill folder (skills/knowledge/retrospective-agent in Ibrahim-3d/orchestrator-supaconductor) into .agents/skills/retrospective-agent in your project. Codex loads it when a task matches its description.

Can I use Retrospective Agent in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Ibrahim-3d/orchestrator-supaconductor --skill retrospective-agent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/retrospective-agent, .gemini/skills/retrospective-agent, .github/skills/retrospective-agent and .opencode/skills/retrospective-agent in your project.

What does Retrospective Agent need to run?

SKILL.md names no scripts, command-line tools or credentials: Retrospective Agent is instructions for the agent only.

Does Retrospective Agent access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Retrospective Agent safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Retrospective Agent use?

Retrospective Agent is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Retrospective Agent use?

About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Retrospective Agent?

Skills that share tags, products or a category with Retrospective Agent: Weekly Engineering Retro (garrytan/gstack, 136k stars), Dough Execute Plan (terryyin/lizard, 2.6k stars), Oral Paper Skill (Adkid-Zephyr/oral-paper-skill, 350 stars) and Deck Retro (asheshgoplani/agent-deck, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Retrospective Agent?

Ibrahim-3d (a GitHub user) maintains it in Ibrahim-3d/orchestrator-supaconductor, which has 381 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on September 27, 2026.

Source: Ibrahim-3d/orchestrator-supaconductor on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.