manage-learn — for Claude Code manage-learn, maestro-flow, community, for Claude Code, ide skills, quality-retrospective, lessons.jsonl, source, **Flags** (capture mode), tag t1,t2

v1.0.0

Acerca de este Skill

Escenario recomendado: Ideal for AI agents that need parse mode → bootstrap store → execute mode → confirm. Resumen localizado: Workflow orchestration CLI with MCP endpoint support and multi-agent dashboard <purpose Pure file-operation CRUD skill for the workflow learning library. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Características

Parse Mode → Bootstrap Store → Execute Mode → Confirm
(capture / (on first use) (Bash/Read/ (INS-id
list / Bash+Write) Write/Grep) + hints)
$ARGUMENTS — mode token followed by options.
$manage-learn "Always read state.json before planning to detect current phase"

# Core Topics

catlog22 catlog22
[103]
[15]
Updated: 4/22/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 10/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution Quality floor passed for review
Review Score
10/11
Quality Score
62
Canonical Locale
en
Detected Body Locale
en

Escenario recomendado: Ideal for AI agents that need parse mode → bootstrap store → execute mode → confirm. Resumen localizado: Workflow orchestration CLI with MCP endpoint support and multi-agent dashboard <purpose Pure file-operation CRUD skill for the workflow learning library. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

¿Por qué usar esta habilidad?

Recomendacion: manage-learn helps agents parse mode → bootstrap store → execute mode → confirm. Workflow orchestration CLI with MCP endpoint support and multi-agent dashboard <purpose Pure file-operation CRUD skill for

Mejor para

Escenario recomendado: Ideal for AI agents that need parse mode → bootstrap store → execute mode → confirm.

Casos de uso accionables for manage-learn

Caso de uso: Applying Parse Mode → Bootstrap Store → Execute Mode → Confirm
Caso de uso: Applying (capture / (on first use) (Bash/Read/ (INS-id
Caso de uso: Applying list / Bash+Write) Write/Grep) + hints)

! Seguridad y limitaciones

  • Limitacion: .workflow/learning/lessons.jsonl — append-only JSONL (shared with quality-retrospective)
  • Limitacion: Bootstrap on demand : Create .workflow/learning/ structure on first use; do not require it to exist.
  • Limitacion: Append-only lessons.jsonl : Never rewrite or delete existing rows.

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is manage-learn?

Escenario recomendado: Ideal for AI agents that need parse mode → bootstrap store → execute mode → confirm. Resumen localizado: Workflow orchestration CLI with MCP endpoint support and multi-agent dashboard <purpose Pure file-operation CRUD skill for the workflow learning library. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

How do I install manage-learn?

Run the command: npx killer-skills add catlog22/maestro-flow/manage-learn. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for manage-learn?

Key use cases include: Caso de uso: Applying Parse Mode → Bootstrap Store → Execute Mode → Confirm, Caso de uso: Applying (capture / (on first use) (Bash/Read/ (INS-id, Caso de uso: Applying list / Bash+Write) Write/Grep) + hints).

Which IDEs are compatible with manage-learn?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for manage-learn?

Limitacion: .workflow/learning/lessons.jsonl — append-only JSONL (shared with quality-retrospective). Limitacion: Bootstrap on demand : Create .workflow/learning/ structure on first use; do not require it to exist.. Limitacion: Append-only lessons.jsonl : Never rewrite or delete existing rows..

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add catlog22/maestro-flow/manage-learn. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use manage-learn immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

manage-learn

Install manage-learn, an AI agent skill for AI agent workflows and automation. Review the use cases, limitations, and setup path before rollout.

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence
<purpose> Pure file-operation CRUD skill for the workflow learning library. No agent spawning, no CLI calls, no LLM inference — just parse-infer-append-confirm. Complements `quality-retrospective`: where retrospective extracts insights in bulk from completed phases, `manage-learn` captures one timeless insight at a time during active work. Both write to the same `lessons.jsonl` store, disambiguated by `source` and `lens` fields.
Parse Mode  →  Bootstrap Store  →  Execute Mode  →  Confirm
(capture /       (on first use)     (Bash/Read/      (INS-id
  list /          Bash+Write)        Write/Grep)      + hints)
  search /
  show)
</purpose> <context> $ARGUMENTS — mode token followed by options.
bash
1$manage-learn "Always read state.json before planning to detect current phase" 2$manage-learn "list --limit 10 --category antipattern" 3$manage-learn "search context propagation" 4$manage-learn "show INS-a3f7b2c1" 5$manage-learn "\"Zod v4 breaks z.object().strict() API\" --category gotcha --tag zod,typescript"

Flags (capture mode):

  • --category <name>pattern|antipattern|decision|tool|gotcha|technique. Default: inferred from text keywords.
  • --tag t1,t2 — Comma-separated tags. Always adds manual implicitly.
  • --phase <N> — Override auto-detected current phase. --phase 0 forces no phase link.
  • --confidence high|medium|low — Default: medium.

Flags (list/search mode):

  • --tag t1,t2 — Filter by tag
  • --category <name> — Filter by category
  • --phase <N> — Filter by phase
  • --lens <name> — Filter by retrospective lens (technical|process|quality|decision)
  • --limit <N> — Row limit (default 20)

Storage:

  • .workflow/learning/lessons.jsonl — append-only JSONL (shared with quality-retrospective)
  • .workflow/learning/learning-index.json — searchable index </context>
<invariants> 1. **No LLM or CLI calls**: This skill is pure file I/O — parse, infer, append, confirm. No `exec_command`, no `spawn_agent`. 2. **Bootstrap on demand**: Create `.workflow/learning/` structure on first use; do not require it to exist. 3. **Append-only lessons.jsonl**: Never rewrite or delete existing rows. 4. **Stable INS-ids**: `INS-{8hex}` from `hash(insightText + timestamp)` — same text at different times gets different ids. 5. **Source field**: Always `"manual"` for captures from this skill; `"retrospective"` is reserved for `quality-retrospective`. 6. **Phase auto-link**: Read `state.json` automatically; `--phase 0` is the only way to force null. 7. **Keyword inference is approximate**: When in doubt, default to `pattern` category rather than prompting user. </invariants> <execution>

Step 1: Parse Mode and Validate Arguments

Parse the first non-flag token from $ARGUMENTS:

First tokenMode
listlist
search followed by querysearch
show followed by INS-idshow
EmptyPrompt with functions.request_user_input
Any other text (quoted or not)capture

Validate --category if provided (allowed: pattern, antipattern, decision, tool, gotcha, technique). E002 if unknown.

Step 2: Bootstrap Learning Store (on first use)

Check if .workflow/learning/lessons.jsonl exists. If not:

javascript
1// Create directory and empty files — use Bash + Write (apply_patch cannot create empty files reliably) 2Bash('mkdir -p .workflow/learning && touch .workflow/learning/lessons.jsonl') 3Write('.workflow/learning/learning-index.json', '{"version":1,"entries":[]}\n')

Verify .workflow/ exists (E001 if not).

Step 3: Execute Mode

Capture Mode

  1. Infer category from insight text (keyword heuristics, no LLM):
Keywords present in textInferred category
always, should, prefer, best practicepattern
never, avoid, don't, pitfall, breaksantipattern
decided, chose, tradeoff, because, reasondecision
tool, library, framework, package, clitool
gotcha, surprising, unexpected, watch outgotcha
technique, approach, method, pattern fortechnique
  1. Auto-link phase: Read .workflow/state.json for current_phase. Resolve matching directory slug from .workflow/phases/. --phase 0 forces null.

  2. Generate stable INS-id: INS-{8 lowercase hex} from hash(insightText + timestamp).

  3. Build lessons.jsonl row:

json
1{ 2 "id": "INS-a3f7b2c1", 3 "title": "<first 80 chars of insight>", 4 "summary": "<full insight text>", 5 "source": "manual", 6 "lens": null, 7 "category": "<inferred or explicit>", 8 "tags": ["manual", "<user tags...>"], 9 "phase": "<N or null>", 10 "phase_slug": "<slug or null>", 11 "confidence": "<high|medium|low>", 12 "routed_to": null, 13 "routed_id": null, 14 "created_at": "<ISO>" 15}
  1. Append to lessons.jsonl:
javascript
1// Append single JSON line — Bash echo avoids rewriting the whole file 2Bash(`echo '${JSON.stringify(insightRow)}' >> .workflow/learning/lessons.jsonl`)
  1. Update learning-index.json: Read, push entry, write back:
javascript
1const index = JSON.parse(Read('.workflow/learning/learning-index.json')) 2index.entries.push({ id: insightRow.id, title: insightRow.title, category: insightRow.category, tags: insightRow.tags, phase: insightRow.phase, created_at: insightRow.created_at }) 3Write('.workflow/learning/learning-index.json', JSON.stringify(index, null, 2) + '\n')

List Mode

Read learning-index.json entries array. Apply filters (--tag, --category, --phase, --lens). Sort newest-first. Display up to --limit rows (default 20):

ID              Category     Phase  Tags              Title
INS-a3f7b2c1   gotcha       3      manual,zod        Zod v4 breaks z.object().strict() API
INS-b1c2d3e4   pattern      2      manual            Always read state.json before planning

Search Mode

Grep across lessons.jsonl for the query string. Rank by field match weight: title (3) > tags (2) > summary (1). Display top matches with ID, category, phase, title.

Show Mode

Validate INS-id format INS-[0-9a-f]{8}. Find row in lessons.jsonl where id matches. Display full record with all fields. If routed_to is set, display the linked artifact path.

Step 4: Display Confirmation

Capture mode:

=== INSIGHT CAPTURED ===
ID:         INS-a3f7b2c1
Category:   gotcha
Phase:      3 (phase-03-api-layer)
Confidence: medium
Tags:       manual, zod, typescript

Next: $manage-learn "list"  or  $manage-learn "search zod"
</execution>

<error_codes>

CodeSeverityDescriptionStage
E001error.workflow/ not initialized — run $maestro-init firstparse_input
E002errorUnknown --category valueparse_input
E003errorshow mode requires INS-id argumentshow
E004errorINS-id not found in lessons.jsonlshow
W001warningAuto-phase detection: current_phase found but no matching directory; phase set to nullcapture
W002warninglearning-index.json row count differs from lessons.jsonl; offer to rebuild indexlist/search
</error_codes>

<success_criteria>

  • Mode parsed correctly (capture, list, search, show)
  • Learning store bootstrapped on first use
  • Capture: category inferred from keywords, phase auto-linked, INS-id generated
  • Capture: row appended to lessons.jsonl (append-only), index updated
  • List: filters applied, newest-first, respects --limit
  • Search: grep with weighted ranking across title/tags/summary
  • Show: full record displayed for valid INS-id
  • No LLM or CLI calls — pure file I/O only </success_criteria>

Habilidades relacionadas

Looking for an alternative to manage-learn or another community skill for your workflow? Explore these related open-source skills.

Ver todo

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
Inteligencia Artificial

widget-generator

Logo of f
f

Generar complementos de widgets personalizables para el sistema de feeds de prompts.chat

149.6k
0
Inteligencia Artificial

flags

Logo of vercel
vercel

El Marco de React

138.4k
0
Navegador

pr-review

Logo of pytorch
pytorch

Tensores y redes neuronales dinámicas en Python con fuerte aceleración de GPU

98.6k
0
Desarrollador