Agent skill

Knowledge Manager

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

Loads relevant patterns and known errors before track planning.

AGPL-3.0Auto-check passedKnowledge Management

Install Knowledge Manager

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

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

GitHub CLI
$ gh skill install Ibrahim-3d/orchestrator-supaconductor knowledge-manager --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/knowledge-manager .claude/skills/knowledge-manager && 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
knowledge-manager
GitHub stars
380
Token cost
~1.6k tokens
SKILL.md length
332 words
Files
1
Skills in repo
27
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Loads relevant patterns and known errors before track planning.

  • Works in 3 steps: Extract Keywords from Spec → Search Pattern Library → Generate Knowledge Brief
  • Knowledge Management work in your project
  • 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

Knowledge Manager is an agent skill from Ibrahim-3d/orchestrator-supaconductor. Loads relevant patterns and known errors before track planning. Searches conductor/knowledge/ for solutions we've used before and errors we've encountered. Injects findings into the planner prompt to prevent reinventing solutions and repeating mistakes. Triggered automatically by orchestrator before PLAN step.

Its SKILL.md is about 1.6k 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 Knowledge Management. It works with Supabase. 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

  • Knowledge Management work in your project

Example prompts

  • “ve used before and errors we”
  • “Use the knowledge-manager skill to load relevant patterns and known errors before track planning”
  • “/knowledge-manager”

Workflow steps

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

  1. Extract Keywords from Spec
  2. Search Pattern Library
  3. Generate Knowledge Brief

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 typescript, markdown and json).

    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

Knowledge Manager loads about 1.6k tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 332 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~82
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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). 332 words, ~1,592 tokens.

Download SKILL.mdSave it as .claude/skills/knowledge-manager/SKILL.md (or your agent's skills folder).
name
knowledge-manager
description
Loads relevant patterns and known errors before track planning. Searches conductor/knowledge/ for solutions we've used before and errors we've encountered. Injects findings into the planner prompt to prevent reinventing solutions and repeating mistakes. Triggered automatically by orchestrator before PLAN step.

Knowledge Manager — Pre-Planning Intelligence

Searches the knowledge base for relevant patterns and errors before a track begins, injecting institutional memory into the planning process.

When This Runs

Automatically — The orchestrator calls this agent BEFORE dispatching the loop-planner for any track.

Inputs

  1. Track spec.md — To understand what the track is about
  2. Track type — From metadata.json (feature, UI, integration, etc.)
  3. Keywords — Extracted from spec (e.g., "auth", "Supabase", "form", "state")

Workflow

1. Extract Keywords from Spec

read_file the track's spec.md and extract relevant keywords:

typescript
const keywords = extractKeywords(spec);
// Example: ["authentication", "Supabase", "login", "signup", "OAuth"]

Keywords come from:

  • Section headings
  • Technical terms
  • Integration names (Supabase, Stripe, Gemini)
  • Component types (form, modal, grid, etc.)
  • Pattern names (state management, API routes, etc.)
2. Search Pattern Library

Search conductor/knowledge/patterns.md for matching patterns. Score each entry by keyword overlap and return only the top 3 highest-scoring results (skip zero-score entries):

markdown
## Relevant Patterns Found (top 3 by relevance)

### Pattern: Supabase Client Singleton
**Category**: Integration
**Relevance score**: 3/5 keywords matched
**Summary**: Use singleton pattern with server/client separation
**Key Code**:
```tsx
// lib/supabase/server.ts
export const createClient = async () => { /* ... */ };
Pattern: Server Actions with Error Handling

Category: API Relevance score: 2/5 keywords matched Summary: Wrap all server actions with try/catch and typed responses


### 3. Search Error Registry

Search `conductor/knowledge/errors.json` for errors related to this track type. Score each entry by keyword overlap and **return only the top 3 highest-scoring results**:

```markdown
## Known Errors to Watch For

### Error: Hydration Mismatch (err-003)
**Pattern**: "Hydration failed because the initial UI does not match"
**Context**: Auth state can differ between server and client
**Prevention**: Wrap auth-dependent UI in useEffect or client component

### Error: NEXT_REDIRECT in try/catch (err-004)
**Pattern**: "NEXT_REDIRECT"
**Context**: Server actions with redirect after login
**Prevention**: Re-throw NEXT_REDIRECT errors or move redirect outside try/catch
4. Generate Knowledge Brief

Output a knowledge brief that gets injected into the planner's prompt. Total output must not exceed 500 tokens. If the top-3 patterns + top-3 errors would exceed this budget, truncate lower-scored entries first:

markdown
# Knowledge Brief for [Track ID]

## Relevant Patterns (Apply These)

1. **Supabase Client Singleton** — Use separate server/client clients
2. **Server Actions with Error Handling** — Typed responses with try/catch

## Known Errors (Avoid These)

1. **Hydration Mismatch** — Don't render auth-dependent UI on server
2. **NEXT_REDIRECT** — Handle redirect() specially in try/catch

## Previous Similar Work

- Track `auth-flow_20260115` implemented similar auth flow
- See `conductor/tracks/auth-flow_20260115/plan.md` for reference

## Recommendations

- Consider using the existing auth patterns from previous track
- Watch for SSR/client hydration issues with auth state

Output Format

The Knowledge Manager returns a structured brief:

json
{
  "patterns_found": [
    {
      "name": "Supabase Client Singleton",
      "category": "Integration",
      "relevance": "high",
      "summary": "...",
      "code_snippet": "..."
    }
  ],
  "errors_to_watch": [
    {
      "id": "err-003",
      "pattern": "Hydration mismatch",
      "prevention": "..."
    }
  ],
  "similar_tracks": [
    {
      "track_id": "auth-flow_20260115",
      "relevance": "Implemented OAuth flow"
    }
  ],
  "recommendations": [
    "Reuse auth patterns from previous track",
    "Watch for hydration issues"
  ]
}

Integration with Orchestrator

The orchestrator injects this brief into the planner's dispatch:

typescript
// In conductor-orchestrator
async function dispatchPlanner(trackId: string) {
  // 1. Run Knowledge Manager first
  const knowledgeBrief = await Task({
    subagent_type: "general-purpose",
    description: "Load knowledge for track",
    prompt: `You are the knowledge-manager agent.

      Track: ${trackId}
      Spec: ${specContent}

      Search conductor/knowledge/patterns.md and errors.json.
      Return a knowledge brief with relevant patterns and errors.`
  });

  // 2. Dispatch planner WITH knowledge brief
  await Task({
    subagent_type: "general-purpose",
    description: "Create track plan",
    prompt: `You are the loop-planner agent.

      ${knowledgeBrief.output}

      Create plan.md using the patterns above where applicable.
      Avoid the known errors listed.`
  });
}

Search Strategies

By Category

Match track type to pattern/error categories:

  • UI track → Search "UI", "component", "styling" patterns
  • Integration track → Search "Integration", "API", "Supabase", "Stripe" patterns
  • Feature track → Search "State", "API", "Testing" patterns
By Keyword

Fuzzy match keywords from spec against pattern descriptions and error contexts.

By Recency

Prioritize patterns from recent tracks (more likely to be relevant to current codebase state).

Maintaining the Knowledge Base

The Knowledge Manager is read_file-only. Writing to the knowledge base is done by:

  • Retrospective Agent — After track completion
  • Fixer Agent — When discovering new error patterns

No Matches Found

If no relevant patterns or errors are found, return:

json
{
  "patterns_found": [],
  "errors_to_watch": [],
  "similar_tracks": [],
  "recommendations": ["No prior patterns found. Document solutions discovered in this track."]
}

This is fine — it means we're doing something new. The retrospective will capture learnings after.

© 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/knowledge-manager of Ibrahim-3d/orchestrator-supaconductor.

Open the folder on GitHubat commit 76c9b10

Compare with similar skills

Knowledge Manager 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.

Knowledge Manager compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Knowledge Manager this skillIbrahim-3d/orchestrator-supaconductor380—~1.6kAutomated safety check: PassAGPL-3.0
Joplinalondmnt/joplin-mcp172—~897Automated safety check: PassMIT
Braindbdimknaf/braindb110—~6.1kAutomated safety check: NotesApache-2.0
Export TemplateHurricaHjz/second-yourself113—~4.8kAutomated safety check: WarnMIT
Obsidian Project Memorybrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~2.4kAutomated safety check: PassCustom licence
AI BrainOotto-AI/claude-content-skills101—~1.1kAutomated safety check: PassMIT

Similar skills

  • Joplin

    alondmnt/joplin-mcp

    Orchestration guidance for Joplin note, notebook, and tag management tools

    172 GitHub stars~897 tokensUpdated 25 days ago
    Knowledge ManagementAuto-check passed
  • Braindb

    dimknaf/braindb

    Memory recall and save. An agent skill from dimknaf/braindb.

    110 GitHub stars~6.1k tokensUpdated 25 days ago
    Knowledge ManagementAuto-check: notes
  • Export Template

    HurricaHjz/second-yourself

    Sync THIS LLM-Wiki framework with its public GitHub repo, ONE direction per run: --push (vault → repo) publishes your framework; --pull (repo → vault) updates your framework from a newer repo version.

    113 GitHub stars~4.8k tokensUpdated 5 days ago
    Knowledge ManagementAuto-check: warnings
  • Obsidian Project Memory

    brycewang-stanford/Auto-Empirical-Research-Skills

    This skill should be used when the user asks to maintain an Obsidian knowledge base for a research project, import an existing research repository into Obsidian, keep project memory or daily notes…

    4.5k GitHub stars~2.4k tokensUpdated 2 days ago
    Knowledge ManagementAuto-check passed
  • AI Brain

    Ootto-AI/claude-content-skills

    Give Claude a permanent, searchable long-term memory using an Obsidian vault as the store.

    101 GitHub stars~1.1k tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed
  • Ade Perf Boot

    arul28/ADE

    Performance patterns discovered for ADE's cold launch and "main screen" surfaces — welcome / project picker, recent projects list, project open flow, remote runtime connect, iOS pairing.

    113 GitHub stars~707 tokensUpdated today
    Knowledge 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.

    380 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…

    380 GitHub starsUsed in 8 repos~2.9k tokens
    Auto-check passed
  • Agent Factory

    Ibrahim-3d/orchestrator-supaconductor

    Creates specialized worker agents dynamically from templates.

    380 GitHub stars~2.9k tokensUpdated 10 days ago
    Auto-check passed
  • Board Of Directors

    Ibrahim-3d/orchestrator-supaconductor

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

    380 GitHub stars~1.9k tokensUpdated 10 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.

    380 GitHub stars~2.1k tokensUpdated 10 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.

    380 GitHub stars~830 tokensUpdated 10 days ago
    Auto-check passed

Works with

Questions about Knowledge Manager

What does Knowledge Manager do?

Loads relevant patterns and known errors before track planning. Knowledge Manager is an agent skill from Ibrahim-3d/orchestrator-supaconductor. Loads relevant patterns and known errors before track planning.

When should I use Knowledge Manager?

Knowledge Manager fits situations like: knowledge Management work in your project.

How do I install Knowledge Manager in Claude Code?

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

How do I install Knowledge Manager in Codex?

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

Can I use Knowledge Manager 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 knowledge-manager -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/knowledge-manager, .gemini/skills/knowledge-manager, .github/skills/knowledge-manager and .opencode/skills/knowledge-manager in your project.

What does Knowledge Manager need to run?

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

Does Knowledge Manager 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 Knowledge Manager 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 Knowledge Manager use?

Knowledge Manager 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 Knowledge Manager use?

About 1.6k tokens (SKILL.md is roughly 6.4k 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 Knowledge Manager?

Skills that share tags, products or a category with Knowledge Manager: Joplin (alondmnt/joplin-mcp, 172 stars), Braindb (dimknaf/braindb, 110 stars), Export Template (HurricaHjz/second-yourself, 113 stars) and Obsidian Project Memory (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Knowledge Manager?

Ibrahim-3d (a GitHub user) maintains it in Ibrahim-3d/orchestrator-supaconductor, which has 380 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.