Agent skill

External Source Research

by bbartling in bbartling/open-fdd

A skill your agent uses when implementation or review depends on external documentation, standards, protocols, APIs, SDKs, changelogs, or version-specific behavior.

Custom licenceAuto-check passedDevelopment

Install External Source Research

skills CLI
$ npx skills add bbartling/open-fdd --skill external-source-research -a claude-code

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

GitHub CLI
$ gh skill install bbartling/open-fdd external-source-research --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/bbartling/open-fdd.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/external-source-research .claude/skills/external-source-research && 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
external-source-research
GitHub stars
172
Token cost
~1.3k tokens
SKILL.md length
567 words
Files
3 (incl. references)
Skills in repo
23
Repo updated
First seen
Licence
Custom licence

At a glance

A skill your agent uses when implementation or review depends on external documentation, standards, protocols, APIs, SDKs, changelogs, or version-specific behavior.

  • Works in 5 steps: Objective: one sentence describing the… → Scope: files, folders, PR diff,… → Constraints: read-only vs write,… → …
  • Review depends on external documentation
  • SKILL.md covers Trigger, Non-goals, Operating principles and Subagent orchestration rules, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

External Source Research is an agent skill from bbartling/open-fdd. Use when implementation or review depends on external documentation, standards, protocols, APIs, SDKs, changelogs, or version-specific behavior. Produces a concise source dossier and implementation implications.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/output-contracts.md` and `references/severity-rubric.md`).

It sits in Development, covering Changelog and release notes and Subagents. The repository describes itself as: Fault Detection Diagnostics (FDD) for HVAC datasets.

When your agent uses it

  • Review depends on external documentation
  • Version-specific behavior

Example prompts

  • “/external-source-research”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Objective: one sentence describing the question to answer.
  2. Scope: files, folders, PR diff, services, packages, or docs to inspect.
  3. Constraints: read-only vs write, commands allowed, network/doc lookup allowed, and timeout.
  4. Required evidence: exact files/symbols/commands/sources to cite.
  5. Output schema: use the schema requested by the skill.

What it can do on your machine

Read from SKILL.md and the folder at commit b5c4e9c. 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).

    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

External Source Research loads about 1.3k tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 59 tokens; SKILL.md has 567 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.8k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 567 words (~1,339 tokens).

“When the task mentions current docs, specifications, protocol behavior, framework/library APIs, cloud provider behavior, compliance text, or anything that may have changed recently.”

— opening of SKILL.md by bbartling, Custom licence
name
external-source-research

Read the full SKILL.md on GitHub

Files

SKILL.md and 2 other files (references) in .agents/skills/external-source-research of bbartling/open-fdd.

  • SKILL.md
  • references/output-contracts.md
  • references/severity-rubric.md

Open the folder on GitHubat commit b5c4e9c

Compare with similar skills

External Source Research 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.

External Source Research compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
External Source Research this skillbbartling/open-fdd172—~1.3kAutomated safety check: PassCustom licence
Utility Pm Changelog Curatorproduct-on-purpose/pm-skills715—~1.1kAutomated safety check: PassApache-2.0
Rigor Queue Releaserigortype/rigor106—~1.7kAutomated safety check: PassMPL-2.0
Utility Pm Release Conductorproduct-on-purpose/pm-skills715—~1.6kAutomated safety check: PassApache-2.0
Simple Englishmoeru-ai/airi50k2 repos~4.6kAutomated safety check: PassMIT
StarRocks Release NotesStarRocks/starrocks12k—~1.9kAutomated safety check: NotesApache-2.0

Similar skills

  • Utility Pm Changelog Curator

    product-on-purpose/pm-skills

    Draft CHANGELOG entries from git log via the pm-changelog-curator sub-agent, applying the repo hygiene rules (describe what changed, public paths only, no attribution trailers).

    715 GitHub stars~1.1k tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • Rigor Queue Release

    rigortype/rigor

    Rank and clear merge-worthy Issues before a Rigor cut, one unit per turn, in an interactive pi session (/queue-release).

    106 GitHub stars~1.7k tokensUpdated today
    DevelopmentAuto-check passed
  • Utility Pm Release Conductor

    product-on-purpose/pm-skills

    Walk the guided 6-gate release runbook (G0 readiness, G1 adversarial review, G2 version bump and CHANGELOG, G2.5 commit and re-verify, G3 tag and push, G4 post-tag hygiene) via the…

    715 GitHub stars~1.6k tokensUpdated 3 days ago
    DevOps & CloudAuto-check passed
  • Simple English

    moeru-ai/airi

    Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop.

    50k GitHub starsUsed in 2 repos~4.6k tokens
    DevelopmentAuto-check passed
  • StarRocks Release Notes

    StarRocks/starrocks

    Drafts English release notes for a StarRocks patch release from the PRs merged into its release branch, then opens a documentation PR and hands translation to /translate.

    12k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check: notes
  • Cutting A Release

    TriliumNext/Trilium

    A skill your agent uses when cutting, preparing, or debugging a Trilium release — bumping the monorepo version, tagging, or diagnosing a failed "Release" workflow run.

    38k GitHub stars~3.2k tokensUpdated today
    DevelopmentAuto-check passed

More from bbartling/open-fdd

All 23 skills in this repo
  • Architecture Design Review

    bbartling/open-fdd

    A skill your agent uses to evaluate architecture, design proposals, refactors, module boundaries, dependency direction, data flow, concurrency model, and maintainability tradeoffs across any codebase.

    172 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Codebase Research Pass

    bbartling/open-fdd

    A skill your agent uses for structured research on an unfamiliar or complex codebase before planning, reviewing, or editing.

    172 GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Multi Agent PR Review

    bbartling/open-fdd

    A skill your agent uses for rigorous pull request, branch, patch, or diff review.

    172 GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • A skill your agent uses to design, run, or review performance work with reproducible A/B baselines.

    172 GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • A skill your agent uses to compare any codebase against a specification, API contract, protocol, policy, RFC, security baseline, or product requirements document.

    172 GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Openfdd Ecm Engineering

    bbartling/open-fdd

    A skill your agent uses when migrating or changing generic ECM math in openfdd.ecmengineering, publishing PyPI ECM workbook exports, or Compare honesty (FITTED vs industry).

    172 GitHub stars~966 tokensUpdated today
    Auto-check passed

Categories

Questions about External Source Research

What does External Source Research do?

A skill your agent uses when implementation or review depends on external documentation, standards, protocols, APIs, SDKs, changelogs, or version-specific behavior. External Source Research is an agent skill from bbartling/open-fdd. Use when implementation or review depends on external documentation, standards, protocols, APIs, SDKs, changelogs, or version-specific behavior.

When should I use External Source Research?

External Source Research fits situations like: review depends on external documentation; version-specific behavior.

How do I install External Source Research in Claude Code?

Run `npx skills add bbartling/open-fdd --skill external-source-research -a claude-code`. Or copy the skill folder (.agents/skills/external-source-research in bbartling/open-fdd) into .claude/skills/external-source-research in your project. Claude Code loads it when a task matches its description.

How do I install External Source Research in Codex?

Run `npx skills add bbartling/open-fdd --skill external-source-research -a codex`. Or copy the skill folder (.agents/skills/external-source-research in bbartling/open-fdd) into .agents/skills/external-source-research in your project. Codex loads it when a task matches its description.

Can I use External Source Research 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 bbartling/open-fdd --skill external-source-research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/external-source-research, .gemini/skills/external-source-research, .github/skills/external-source-research and .opencode/skills/external-source-research in your project.

What does External Source Research need to run?

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

Does External Source Research 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 External Source Research 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 External Source Research use?

External Source Research has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does External Source Research use?

About 1.3k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 473 tokens, read only when the agent opens those files.

What are the alternatives to External Source Research?

Skills that share tags, products or a category with External Source Research: Utility Pm Changelog Curator (product-on-purpose/pm-skills, 715 stars), Rigor Queue Release (rigortype/rigor, 106 stars), Utility Pm Release Conductor (product-on-purpose/pm-skills, 715 stars) and Simple English (moeru-ai/airi, 50k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains External Source Research?

bbartling (a GitHub user) maintains it in bbartling/open-fdd, which has 172 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 7, 2026.

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