Przejdź do treści
Biblioteka skilli
AI i agenci · Budowanie i kod

skill-writer

/skill-writer

Tworzy, syntetyzuje ze źródeł i iteracyjnie ulepsza skille agentów zgodnie ze specyfikacją Agent Skills, z przechwytywaniem źródeł, bramkami głębokości, rejestracją i walidacją.

Repozytorium
warden ↗
Licencja
Apache-2.0
Ostatnia zmiana repozytorium
23.10.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
45
Skrypty
2
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 23.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

Co sprawdzić przed instalacją
  • 2 skrypty w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.

Skrypty: scripts/quick_validate.py, scripts/quick_validate_test.py

Co robi i kiedy

Tworzy, syntetyzuje ze źródeł i iteracyjnie ulepsza skille agentów zgodnie ze specyfikacją Agent Skills, z przechwytywaniem źródeł, bramkami głębokości, rejestracją i walidacją.

Wyzwalacze z opisu

create a skillwrite a skillsynthesize sources into a skillimprove a skill from positive/negative examplesupdate a skillmaintain skill docs and registration
Oryginalny opis (EN)

Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Use when asked to "create a skill", "write a skill", "synthesize sources into a skill", "improve a skill from positive/negative examples", "update a skill", or "maintain skill docs and registration". Handles source capture, depth gates, authoring, registration, and validation.

Jak działa

  1. Core Workflow References
  2. Artifact Layout References
  3. Workflow Mechanic References
  4. Claude Code References
  5. Example Profiles
  6. Step 1: Resolve target, path, and shape
  7. Step 2: Run synthesis when needed
  8. Step 3: Run iteration first when improving from outcomes/examples
  9. Step 4: Author or update skill artifacts
  10. Step 5: Optimize description quality
Sekcje z nagłówków SKILL.md, w oryginale · 156 linii, 1 194 słów
Podgląd SKILL.md
---
name: skill-writer
description: Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Use when asked to "create a skill", "write a skill", "synthesize sources into a skill", "improve a skill from positive/negative examples", "update a skill", or "maintain skill docs and registration". Handles source capture, depth gates, authoring, registration, and validation.
---

# Skill Writer

Use this as the single canonical workflow for skill creation and improvement.
Primary success condition: maximize high-value input coverage before authoring while minimizing wasted runtime tokens.

Load only the path(s) required for the task. `SKILL.md` is the primary router: every bundled reference file should have a direct "open when..." reason here.

## Core Workflow References

| Open when you need to... | Read |
|--------------------------|------|
| choose the minimum workflow path for create, update, iterate, or research-first work | `references/mode-selection.md` |
| choose the simplest adequate execution shape before deciding files | `references/execution-shapes.md` |
| apply writing constraints for depth, concision, and portability | `references/design-principles.md` |
| decide what belongs in `SKILL.md`, `references/`, `SPEC.md`, or subfolders | `references/reference-architecture.md` |
| create or update the maintenance contract for a skill | `references/spec-template.md` |
| find missing high-signal sources, including history and regressions | `references/source-discovery.md` |
| run the full synthesis pass with depth gates and source capture | `references/synthesis-path.md` |
| author or update `SKILL.md`, `SPEC.md`, and supporting files | `references/authoring-path.md` |
| improve trigger language and false-positive/false-negative behavior | `references/description-optimization.md` |
| iterate from positive, negative, or fix examples | `references/iteration-path.md` |
| store persistent working and holdout examples for future revisions | `references/iteration-evidence.md` |
| choose a response template, schema, or output contract | `references/output-contracts.md` |
| troubleshoot overloaded layouts, hidden refs, or other structure failures | `references/structure-troubleshooting.md` |
| verify a risky, disputed, or explicitly requested change | `references/evaluation-path.md` |
| register the skill and run final validation checks | `references/registration-validation.md` |

## Artifact Layout References

| Open when you need to... | Read |
|--------------------------|------|
| keep the whole skill inline in one coherent `SKILL.md` | `references/artifact-layouts/inline-skill-layout.md` |
| split optional deep knowledge into focused routed references | `references/artifact-layouts/reference-backed-skill-layout.md` |
| add scripts for deterministic automation or validation | `references/artifact-layouts/script-backed-skill-layout.md` |
| define a skill that is usually invoked with explicit arguments | `references/artifact-layouts/argument-driven-skill-layout.md` |
| ship reusable templates, schemas, or other static assets | `references/artifact-layouts/asset-template-skill-layout.md` |

## Workflow Mechanic References

| Open when you need to... | Read |
|--------------------------|------|
| break a task into fixed ordered steps | `references/workflow-mechanics/prompt-chaining.md` |
| classify requests and route them to different downstream paths | `references/workflow-mechanics/routing-workflows.md` |
| split independent work into parallel units or votes | `references/workflow-mechanics/parallel-workflows.md` |
| discover work units dynamically and coordinate worker outputs | `references/workflow-mechanics/orchestrator-workers.md` |
| critique and revise output against a rubric | `references/workflow-mechanics/evaluator-loops.md` |
| run validate-fix-repeat checks during authoring or execution | `references/workflow-mechanics/validation-loops.md` |
| validate a plan before executing a risky action | `references/workflow-mechanics/plan-validate-execute.md` |

## Claude Code References

| Open when you need to... | Read |
|--------------------------|------|
| use Claude-specific frontmatter or invocation controls | `references/claude-code/frontmatter-and-invocation.md` |
| use Claude argument fields or substitution variables | `references/claude-code/argument-substitutions.md` |
| build a skill that runs in isolated `context: fork` | `references/claude-code/subagent-fork-skills.md` |
| build a skill that uses Claude hooks for deterministic enforcement | `references/claude-code/hook-backed-skills.md` |
| use Claude shell preprocessing for dynamic context injection | `references/claude-code/dynamic-context.md` |

## Example Profiles

| Open when you need to... | Read |
|--------------------------|------|
| see the expected depth for a documentation-heavy skill | `references/examples/documentation-skill.md` |
| see the expected depth for a security-review skill | `references/examples/security-review-skill.md` |
| see the expected depth for a workflow-process skill | `references/examples/workflow-process-skill.md` |
| see what a good routed skill looks like | `references/examples/router-skill.md` |
| see what a good evaluator-loop skill looks like | `references/examples/evaluator-loop-skill.md` |
| see what a good subagent-fork skill looks like | `references/examples/subagent-fork-skill.md` |
| see what a good hook-backed skill looks like | `references/examples/hook-backed-skill.md` |

## Step 1: Resolve target, path, and shape

1. Resolve the intended operation (`create`, `update`, `synthesize`, `iterate`) and inspect workspace prior art before choosing where files belong.
2. Choose the target skill root from observed conventions. If the canonical location is still unclear after inspection, ask one direct question before editing files.
3. Read `references/mode-selection.md` to choose the minimum required workflow paths.
4. Read `references/execution-shapes.md` to choose the primary execution shape.
5. Default to the simplest adequate shape. If selecting a more complex shape, record why simpler shapes were rejected.
6. Load only the exact artifact-layout, workflow-mechanic, and provider-specific leaf files required by that shape.
7. Record portability implications before using provider-specific mechanics.

## Step 2: Run synthesis when needed

Read `references/synthesis-path.md`.

1. Use this path for new skills, material changes, and research-first planning.
2. Collect and score relevant sources with provenance.
3. Read `references/source-discovery.md` when source material is thin, stale, or ambiguous.
4. Produce source-backed decisions and coverage/gap status, including the class and execution-shape choice.
5. Load example profiles only when they add concrete depth for the selected class or shape.
6. If the skill uses provider-specific mechanics, include current official provider docs and capture usage constraints.
7. Do not move to authoring until depth gates pass.

## Step 3: Run iteration first when improving from outcomes/examples

Read `references/iteration-path.md` first when selected path includes `iteration` (for example operation `iterate`).

1. Capture and anonymize examples with provenance.
2. Read `references/iteration-evidence.md` when examples should persist beyond the current turn.
3. Re-evaluate skill behavior against working and holdout slices.
4. Propose improvements from positive/negative/fix evidence.
5. Carry concrete behavior deltas into authoring.

Skip this step when selected path does not include `iteration`.

## Step 4: Author or update skill artifacts

Read `references/authoring-path.md`.

1. Write or update `SKILL.md` in imperative voice with trigger-rich description.
2. Keep `SKILL.md` as the runtime router, not an encyclopedia.
3. Read `references/reference-architecture.md` before adding bulk instructions or new reference files.
4. Create or update `SPEC.md` using `references/spec-template.md` when creating a new skill or materially changing its contract.
5. Create focused reference files, subfolders, scripts, and assets only when each one has a clear "open when..." reason.
6. If you add a bundled reference file, add a direct routing entry for it in this `SKILL.md`.
7. Prefer checklists, tables, templates, and input/output examples over explanatory prose.
8. Follow only the specific artifact-layout, workflow-mechanic, Claude-specific, and output-contract references selected for this skill.
9. For advanced execution shapes, add the required routing, delegation, or safety contracts before considering the skill complete.
10. For authoring/generator skills, include transformed examples in references:
   - happy-path
   - secure/robust variant
   - anti-pattern + corrected version

## Step 5: Optimize description quality

Read `references/description-optimization.md`.

1. Validate should-trigger and should-not-trigger query sets.
2. Reduce false positives and false negatives with targeted description edits.
3. Keep trigger language generic across providers unless the skill is intentionally provider-specific.

## Step 6: Evaluate only when needed

1. Read `references/evaluation-path.md` only when the user asks for evaluation, the change is high-risk, or the architecture choice is non-obvious.
2. If you run evaluation, start with the lightweight qualitative check.
3. Run deeper evals only when requested or risk warrants it.
4. Record outcomes and unresolved risks when evaluation is run.

## Step 7: Register and validate

Read `references/registration-validation.md`.

1. Apply repository registration steps for the active layout you verified in the workspace.
2. Run quick validation with strict depth gates.
3. Reject shallow outputs that fail depth gates or required artifact checks.

## Output format

Return:

1. `Summary`
2. `Changes Made`
3. `Validation Results`
4. `Open Gaps`
Pliki w paczce (45)
  • EVAL.md 5 KB
  • SKILL.md 10 KB
  • SOURCES.md 14 KB
  • SPEC.md 10 KB
  • references/authoring-path.md 3 KB
  • references/description-optimization.md 1 KB
  • references/design-principles.md 3 KB
  • references/evaluation-path.md 3 KB
  • references/execution-shapes.md 4 KB
  • references/iteration-evidence.md 3 KB
  • references/iteration-path.md 1 KB
  • references/mode-selection.md 4 KB
  • references/output-contracts.md 1 KB
  • references/reference-architecture.md 2 KB
  • references/registration-validation.md 4 KB
  • references/source-discovery.md 3 KB
  • references/spec-template.md 2 KB
  • references/structure-troubleshooting.md 4 KB
  • references/synthesis-path.md 3 KB
  • references/artifact-layouts/argument-driven-skill-layout.md 1 KB
  • references/artifact-layouts/asset-template-skill-layout.md 1 KB
  • references/artifact-layouts/inline-skill-layout.md 1 KB
  • references/artifact-layouts/reference-backed-skill-layout.md 1 KB
  • references/artifact-layouts/script-backed-skill-layout.md 1 KB
  • references/claude-code/argument-substitutions.md 1 KB
  • references/claude-code/dynamic-context.md 1 KB
  • references/claude-code/frontmatter-and-invocation.md 1 KB
  • references/claude-code/hook-backed-skills.md 1 KB
  • references/claude-code/subagent-fork-skills.md 1 KB
  • references/examples/documentation-skill.md 3 KB
  • references/examples/evaluator-loop-skill.md 1 KB
  • references/examples/hook-backed-skill.md 1 KB
  • references/examples/router-skill.md 1 KB
  • references/examples/security-review-skill.md 3 KB
  • references/examples/subagent-fork-skill.md 1 KB
  • references/examples/workflow-process-skill.md 2 KB
  • references/workflow-mechanics/evaluator-loops.md 1 KB
  • references/workflow-mechanics/orchestrator-workers.md 1 KB
  • references/workflow-mechanics/parallel-workflows.md 1 KB
  • references/workflow-mechanics/plan-validate-execute.md 1 KB
  • references/workflow-mechanics/prompt-chaining.md 1 KB
  • references/workflow-mechanics/routing-workflows.md 1 KB
  • references/workflow-mechanics/validation-loops.md 1 KB
  • scripts/quick_validate.py 5 KB
  • scripts/quick_validate_test.py 2 KB

Wersje

RepozytoriumWynikLicencja
Ta strona · getsentry/warden100Apache-2.0
shimo4228/claude-harness100MIT
pytorch/pytorch100BSD-3-Clause
lessweb/deepcode-cli100MIT
qgadrian/aidrian100Apache-2.0
FrancoStino/opencode-skills-collection100MIT
tencentblueking/bk-ci100MIT
ivy00johns/skill-madness100MIT
getsentry/skills100Apache-2.0

Migawka bazy z 13.11.2026 · wersja paczki 33238ef137ef (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 100skill-creator
    Tworzy nowe skille agentów AI dla Prowler zgodnie ze specyfikacją i zasadami projektu, z nagłówkiem i rejestracją w AGENTS.md.
  • 100skill-creation
    Tworzy i przebudowuje Agent Skills zgodnie ze specyfikacją agentskills.io, zamienia prompty w skille i waliduje strukturę.
  • 100write-skill
    Tworzy nowy skill albo ulepsza istniejący w repozytorium skilli, zgodnie z jego zasadami porządkowania.
  • 98skill-authoring
    Tworzy, edytuje i publikuje Agent Skill w repozytorium skilli, w tym plik SKILL.md, i wysyła zmiany na GitHub.
  • 100skill-master
    Tworzy, edytuje, waliduje, benchmarkuje i ulepsza skille zgodnie ze specyfikacją agentskills.io, w tym struktury folderów, wchłanianie zewnętrznej dokumentacji, testy wyzwalania i ślepe porównania A/B.
  • 100skill-creator
    Tworzy i ulepsza skille agenta Claude Code, pisze pliki SKILL.md, poprawia ich wykrywalność, diagnozuje brak aktywacji i odpowiada na pytania o dobre praktyki.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.