Agent skill

Reskill

by bradygaster in bradygaster/squad

Extract durable operating knowledge before slimming or replacing team charters

MITAuto-check passed

Install Reskill

skills CLI
$ npx skills add bradygaster/squad --skill reskill -a claude-code

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

GitHub CLI
$ gh skill install bradygaster/squad reskill --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/bradygaster/squad.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.copilot/skills/reskill .claude/skills/reskill && 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
reskill
GitHub stars
3.3k
Token cost
~1.4k tokens
SKILL.md length
648 words
Files
1
Skills in repo
31
Repo updated
First seen
Licence
MIT

At a glance

Extract durable operating knowledge before slimming or replacing team charters

  • Works in 4 steps: Audit → Extract → Trim → …
  • SKILL.md covers Context, Process, Patterns and Anti-Patterns
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Reskill is an agent skill from bradygaster/squad. Extract durable operating knowledge before slimming or replacing team charters

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Squad: AI agent teams for any project. The licence is MIT.

Example prompts

  • “/reskill”

Workflow steps

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

  1. Audit
  2. Extract
  3. Trim
  4. Report

What it can do on your machine

Read from SKILL.md and the folder at commit d2364df. 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.

    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

Reskill loads about 1.4k tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 648 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 bradygaster/squad at commit d2364df, republished under its MIT licence (© bradygaster). 648 words, ~1,433 tokens.

Download SKILL.mdSave it as .claude/skills/reskill/SKILL.md (or your agent's skills folder).
name
reskill
description
Extract durable operating knowledge before slimming or replacing team charters
domain
team-optimization
confidence
high
source
manual — reduce per-agent context overhead

Context

When the coordinator hears "team, reskill" (or similar: "optimize context", "slim down charters"), trigger a team-wide optimization pass. The goal: reduce per-agent context consumption by extracting shared patterns from charters and histories into reusable skills.

This is a periodic maintenance activity. Run whenever charter/history bloat is suspected or a team will be re-cast. Charters and histories are evidence, not the authority for current product behavior: reconcile candidates against current source, workflows, tests, documentation, skills, and decisions before preserving them.

Process

Step 1: Audit

Read all active agent charters and histories, then inventory existing skills. Measure byte sizes. Identify:

  • Boilerplate — sections repeated across ≥3 charters with <10% variation (collaboration, model, boundaries template)
  • Shared knowledge — domain knowledge duplicated in 2+ charters (incident postmortems, technical patterns)
  • Mature learnings — recurring history lessons that should be promoted to skills
  • Retirement-critical knowledge — any still-current reusable procedure, constraint, incident lesson, or repository operating fact that would be lost if a charter or history were deleted
Step 2: Extract

For each reconciled pattern:

  1. Create or update the skill in the location that matches its activation surface: .squad-templates/skills/{skill-name}/SKILL.md for reusable skills shipped in generated Squad templates, .github/skills/{skill-name}/SKILL.md for repository-local or GitHub Agentic Workflow procedures, or .squad/skills/{skill-name}/SKILL.md for Squad-specific coordinator procedures. Do not treat .copilot/skills/ as a destination for new skills; it is the legacy install path.
  2. Follow the skill template format (frontmatter + Context + Patterns + Examples + Anti-Patterns)
  3. Keep the location consistent with the procedure's real entry point instead of copying the same contract into multiple trees without intent
  4. Set confidence from the evidence, not the number of charters that contained it
Step 3: Trim

Charters — target ≤1.5KB per agent:

  • Remove Collaboration section entirely (spawn prompt + agent-collaboration skill covers it)
  • Remove Voice section (tagline blockquote at top of charter already captures it)
  • Trim Model section to single line: **Preferred:** {model}
  • Remove "When I'm unsure" boilerplate from Boundaries
  • Remove durable operating knowledge now covered by a skill — add a skill reference only when it helps the role activate the procedure
  • Keep: Identity, What I Own, unique How I Work patterns, Boundaries (domain list only)

Histories — target ≤8KB per agent:

  • Apply history-hygiene only when a retained history would otherwise assert a materially false operational fact
  • Promote reusable current patterns even when found in one retiring charter or history
  • Summarize old entries into ## Core Context section
  • Remove session-specific metadata (dates, branch names, requester names)

For a planned re-cast, avoid cosmetic history rewrites. Extract the reusable lesson, document stale or conflicting material in the reskill report, and leave archival cleanup to the re-cast.

Show full SKILL.md (225 more words)Show less
Step 4: Report

Output a savings table:

AgentCharter BeforeCharter AfterHistory BeforeHistory AfterSaved

Include totals and percentage reduction.

Patterns

Minimal Charter Template (target format after reskill)
# {Name} — {Role}

> {Tagline — one sentence capturing voice and philosophy}

## Identity
- **Name:** {Name}
- **Role:** {Role}
- **Expertise:** {comma-separated list}

## What I Own
- {bullet list of owned artifacts/domains}

## How I Work
- {unique patterns and principles — NOT boilerplate}

## Boundaries
**I handle:** {domain list}
**I don't handle:** {explicit exclusions}

## Model
**Preferred:** {model}
Skill Extraction Threshold
  • Normal maintenance: extract repeated operational knowledge; retain genuinely role-specific identity and working style.
  • Before a re-cast: extract every still-current reusable operating rule, even if it appears in a single retiring charter or history.
Conflict Resolution
  1. Current implementation, executable workflows, and tests
  2. Current user-facing documentation and current skills
  3. Decisions that remain applicable
  4. Charter and history records

Do not preserve historical assignments, status reports, personality, ownership, stale version facts, or obsolete workarounds. Record intentionally discarded conflicts in the reskill report.

Source and Mirror Discipline

.squad-templates/skills/ is the canonical source for shipped Squad skill templates. After changing a shipped template, run the repository's skill-template sync command and verify the root, CLI, and SDK mirrors are byte-identical. Local .copilot/skills/ guidance is maintained separately and must not be treated as a generated mirror.

Anti-Patterns

  • Don't delete unique per-agent identity or domain-specific knowledge
  • Don't leave reusable knowledge in a retiring charter just because only one agent recorded it
  • Don't merge unrelated patterns into a single mega-skill
  • Don't remove Model preference line (coordinator needs it for model selection)
  • Don't touch .squad/decisions.md during reskill
  • Don't remove the tagline blockquote — it's the charter's soul in one line

© bradygaster, MIT. 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 .copilot/skills/reskill of bradygaster/squad.

Open the folder on GitHubat commit d2364df

Compare with similar skills

Reskill 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.

Reskill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Reskill this skillbradygaster/squad3.3k—~1.4kAutomated safety check: PassMIT
Extractalirezarezvani/claude-skills28k—~1.4kAutomated safety check: PassMIT
Operator Approval Loopaffaan-m/ECC274k—~3.3kAutomated safety check: PassMIT
Extractactionbook/actionbook1.6k2 repos~3.4kAutomated safety check: PassApache-2.0
It Operationsdavila7/claude-code-templates32k1 repos~3.7kAutomated safety check: PassMIT
Brand Extractnexu-io/open-design100k—~3.1kAutomated safety check: PassApache-2.0

Similar skills

  • Extract

    alirezarezvani/claude-skills

    Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples.

    28k GitHub stars~1.4k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Operator approval contract with internal filing notices for agent-drafted outbound messages, hashed drafts, epoch-keyed decisions, durable delivery claims and receipts, and a pre-draft baseline gate.

    274k GitHub stars~3.3k tokensUpdated 2 days ago
    Auto-check passed
  • Extract

    actionbook/actionbook

    Extract structured data from websites and produce an executable Playwright script plus extracted data.

    1.6k GitHub starsUsed in 2 repos~3.4k tokens
    Sales & SupportAuto-check passed
  • It Operations

    davila7/claude-code-templates

    Manages IT infrastructure, monitoring, incident response, and service reliability.

    32k GitHub starsUsed in 1 repo~3.7k tokens
    DevOps & CloudAuto-check passed
  • Brand Extract

    nexu-io/open-design

    Extract a complete Brand Kit from a live website by driving the in-app browser.

    100k GitHub stars~3.1k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Design Extract

    nexu-io/open-design

    Extract design tokens (color / typography / spacing) from imported source code, screenshots, or Figma exports into the canonical token bag token-map consumes.

    100k GitHub stars~549 tokensUpdated yesterday
    Frontend & DesignAuto-check passed

More from bradygaster/squad

All 31 skills in this repo
  • Fact Checking

    bradygaster/squad

    Review and validate claims using counter-hypothesis testing.

    3.3k GitHub stars~503 tokensUpdated yesterday
    Auto-check passed
  • Architectural Review

    bradygaster/squad

    How to review PRs for architectural quality — module boundaries, dependency direction, export surface, pattern consistency

    3.3k GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed
  • Archival Integrity

    bradygaster/squad

    Preserve content when moving entries between tracked Squad state files

    3.3k GitHub stars~735 tokensUpdated yesterday
    Auto-check passed
  • CI Validation Gates

    bradygaster/squad

    Defensive CI/CD patterns: semver validation, token checks, retry logic, and draft detection

    3.3k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • CLI Wiring

    bradygaster/squad

    Checklist and patterns for wiring new CLI commands into cli-entry.ts

    3.3k GitHub stars~501 tokensUpdated yesterday
    Auto-check passed
  • Enables squad agents on different machines to share work via git-based task queuing

    3.3k GitHub stars~2.7k tokensUpdated yesterday
    Auto-check passed

Questions about Reskill

What does Reskill do?

Extract durable operating knowledge before slimming or replacing team charters. Reskill is an agent skill from bradygaster/squad.

How do I install Reskill in Claude Code?

Run `npx skills add bradygaster/squad --skill reskill -a claude-code`. Or copy the skill folder (.copilot/skills/reskill in bradygaster/squad) into .claude/skills/reskill in your project. Claude Code loads it when a task matches its description.

How do I install Reskill in Codex?

Run `npx skills add bradygaster/squad --skill reskill -a codex`. Or copy the skill folder (.copilot/skills/reskill in bradygaster/squad) into .agents/skills/reskill in your project. Codex loads it when a task matches its description.

Can I use Reskill 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 bradygaster/squad --skill reskill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reskill, .gemini/skills/reskill, .github/skills/reskill and .opencode/skills/reskill in your project.

What does Reskill need to run?

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

Does Reskill 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 Reskill 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 Reskill use?

Reskill is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Reskill use?

About 1.4k tokens (SKILL.md is roughly 5.7k 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 Reskill?

Skills that share tags, products or a category with Reskill: Extract (alirezarezvani/claude-skills, 28k stars), Operator Approval Loop (affaan-m/ECC, 274k stars), Extract (actionbook/actionbook, 1.6k stars) and It Operations (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Reskill?

bradygaster (a GitHub user) maintains it in bradygaster/squad, which has 3,256 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on October 6, 2026.

Source: bradygaster/squad on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.