skf-quick-skill
Skill7 starsChanged 8 days agoApache-2.0View on GitHub
Fast skill from a package name or GitHub URL — no brief needed. Use when the user requests a "quick skill" or "skill from URL" or "skill from package.
In this repository38 other files it gives its agents.
- _skf-learn/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- bmad-advanced-elicitationSkill
- bmad-brainstormingSkill
- bmad-cis-agent-brainstorming-coachSkill
- bmad-cis-agent-creative-problem-solverSkill
- bmad-cis-agent-design-thinking-coachSkill
- bmad-cis-agent-innovation-strategistSkill
- bmad-cis-agent-presentation-masterSkill
- bmad-cis-agent-storytellerSkill
- bmad-cis-design-thinkingSkill
- bmad-cis-innovation-strategySkill
- bmad-cis-problem-solvingSkill
- bmad-cis-storytellingSkill
- bmad-distillatorSkill
- bmad-editorial-review-proseSkill
- bmad-editorial-review-structureSkill
- bmad-helpSkill
- bmad-index-docsSkill
- bmad-party-modeSkill
- bmad-review-adversarial-generalSkill
- bmad-review-edge-case-hunterSkill
- bmad-shard-docSkill
- skf-analyze-sourceSkill
- skf-audit-skillSkill
- skf-brief-skillSkill
- skf-campaignSkill
- skf-create-skillSkill
- skf-create-stack-skillSkill
- skf-drop-skillSkill
- skf-export-skillSkill
- skf-forgerSkill
- skf-refine-architectureSkill
- skf-rename-skillSkill
- skf-setupSkill
- skf-test-skillSkill
- skf-update-skillSkill
- skf-verify-stackSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
Never fabricate content — all data must come from source extraction or user input
- Distinctive: line 28
Never write into a skill folder SKF did not generate
- Distinctive: line 29
Only load one step file at a time — never preload future steps
- Very specific: line 31
Always communicate in {communication_language}
- Very specific: line 34
If {headless_mode} is true, print the one-line JSON progress events on stderr that references/halt-contract.md (Headless Events) defines: …
- Very specific: line 61
Read {project-root}/_bmad/skf/config.yaml and resolve project_name, output_folder, user_name, communication_language, …
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Quick Skill
Overview
The fastest path to a skill — accept a GitHub URL or package name, resolve to source, extract the public API surface, and produce a best-effort SKILL.md with context snippet and metadata. No brief needed. Output is always community-tier quality, regardless of which tools are available.
Conventions
- Bare paths (e.g.
references/<name>.md) resolve from the skill root,{skill-root}: this skill's installed directory, wherecustomize.tomllives. {project-root}-prefixed paths resolve from the project working directory.- Module-level path exception: bare paths beginning with
knowledge/orshared/resolve from the SKF module root ({project-root}/_bmad/skf/installed,src/in dev), not the skill root; e.g.shared/health-check.md, which the terminal step chains to. - Sibling skills: a path that names another SKF skill's folder (
skf-<name>/...) resolves from the SKF module root, and that skill must be installed with this one.
Role
You are a rapid skill compiler collaborating with a developer. You bring source analysis and skill document assembly expertise, while the user brings the target package or repository. Work together efficiently — speed is the priority.
Workflow Rules
These rules apply to every step in this workflow:
- Never fabricate content — all data must come from source extraction or user input
- Never write into a skill folder SKF did not generate
- Only load one step file at a time — never preload future steps
- Run every subagent in the foreground, passing
run_in_background: falseon every Agent call (Claude Code runs a subagent in the background when the flag is left out), with parallel ones as several such calls in one message, and wait for every long-running command to exit before the next instruction; in a headless run, never end a turn while either still runs, since underclaude -pa run stops when its turn ends. - Always communicate in
{communication_language} - Universal cancel-line affordance: at any interactive prompt the user may type
cancel,exit,:q, or select the[X] Cancel and exitmenu option (where surfaced) to leave cleanly. HARD HALT with exit code 6 (user-cancelled): stage{"phase": "<the step's slug>", "halt_reason": "user-cancelled", "reason": "Cancelled. No files were written.", "skill_package": null}as{run_dir}/halt.jsonand runuv run {emitEnvelopeHelper} emit-halt --workflow skf-quick-skill --run-dir "{run_dir}" --target stderr < "{run_dir}/halt.json"(references/halt-contract.md). In step 4 §6 the equivalent affordance is[Q] Quit without writing, with the same exit code and envelope. - If
{headless_mode}is true, auto-proceed through confirmation gates with their default action, and record each auto-decision in the run folder the moment its gate decides, so the envelope'sheadless_decisionscarries it: stage{"gate": "<the gate's name>", "default_action": "<X>", "taken_action": "<X>", "reason": "headless: <why>"}as{run_dir}/decision.jsonand runuv run {emitEnvelopeHelper} record --workflow skf-quick-skill --run-dir "{run_dir}" --decision < "{run_dir}/decision.json". Each gate names its gate and default where it decides. - If
{headless_mode}is true, print the one-line JSON progress events on stderr thatreferences/halt-contract.md(Headless Events) defines: when each step starts, just before it chains on, and at a HARD HALT.
Stages
| # | Step | File | Auto-proceed |
| 1 | Resolve Target | references/resolve-target.md | Conditional (no target, or an ambiguous one) |
| 2 | Ecosystem Check | references/ecosystem-check.md | Conditional (an official skill matches) |
| 3 | Quick Extract | references/quick-extract.md | Conditional (an unusual repo shape, zero exports) |
| 4 | Compile | references/compile.md | No (review) |
| 5 | Write & Validate | references/write-and-validate.md | Conditional (the skill folder exists) |
| 6 | Finalize | references/finalize.md | Yes |
| 7 | Workflow Health Check | references/health-check.md | Yes |
Invocation Contract
| Aspect | Detail |
| Inputs | target (GitHub URL, package name or npm, PyPI or crates.io page URL) [required for single-target mode], language_hint [optional, --language-hint], scope_hint [optional, --scope-hint] |
| Overrides | --language-hint, --scope-hint, --description, --exports, --skip-snippet, --no-active-pointer, --batch <file>, --fail-fast: see On Activation step 4 |
| Gates | step 1: target input, ambiguous package name [C/n/U/X] (if another registry also holds the name; headless keeps the first registry's pick), multi-language disambiguation [C/n/A] (pick any detected language); step 2: ecosystem match [P/I/A] (none until agentskills.io has a registry API); step 3: repo-shape [C/A] + zero-exports rescue [R/P/A]; step 4: review [C/E/S/Q]; step 5: overwrite [Y/N] |
| Outputs | SKILL.md, context-snippet.md, metadata.json, active pointer, result contract (timestamped + -latest copy), one SKF_QUICK_SKILL_RESULT_JSON line (stdout when the run finishes, stderr at a HARD HALT), and under --batch the batch summary. Snippet and active pointer can be skipped per overrides. |
| Headless | All gates auto-resolve with default action when {headless_mode} is true; each auto-decision is recorded in the envelope's headless_decisions. A caller reads the run's own SKF_QUICK_SKILL_RESULT_JSON line. A run that printed no envelope line has no result to read, whatever the process exit code: it was cut off, or could not write its result, and the result contract's -latest copy may then describe an earlier run, so it is never read in its place. Under --batch, a caller reads the batch's batch_summary event and the summary file its summary_path names, never the batch summary's -latest copy in its place: that copy holds the last batch summary written, which may be another batch's. A printed batch_summary event stays the batch's result even if a halt line follows it. A batch that printed no batch_summary event has no batch result, whatever the process exit code: a halt line of its own (phase batch-mode, or on-activation) says why it stopped, and with no halt line it was cut off or could not print its halt line. A target it printed a done or fail event for ended as that event says; a target with a start event and no end event has no result, and a target with no event did not run in this session. |
| Exit codes | See references/halt-contract.md: the exit-code map and the envelope every HARD HALT emits, except On Activation step 1's check for python3 and uv, which prints none |
On Activation
Read
{project-root}/_bmad/skf/config.yamland resolveproject_name,output_folder,user_name,communication_language,document_output_language,skills_output_folder,forge_data_folderandsidecar_path.Then check the runtime: every helper this workflow runs, the envelope emitter included, runs through
uv run, so confirm thatpython3anduvare both on$PATH(command -v python3andcommand -v uv). If either is missing, HARD HALT with exit code 3 (resolution-failure): display "Quick Skill needs{the missing tool}, which is not on your PATH. Install it (uvfrom https://docs.astral.sh/uv/getting-started/installation/,python3from https://www.python.org/downloads/), then re-run." No envelope is printed: the emitter needsuvtoo.Then resolve
{emitEnvelopeHelper}← the first existing path of{project-root}/_bmad/skf/shared/scripts/skf-emit-result-envelope.pyand{project-root}/src/shared/scripts/skf-emit-result-envelope.py, the shared emitter every envelope and auto-decision goes through, and create the run folder:mkdir -p "{project-root}/_bmad-output/.skf-run" && mktemp -d "{project-root}/_bmad-output/.skf-run/skf-quick-skill-XXXXXXXX"Bind
{run_dir}← the path it prints (a finished run deletes it; a halted one keeps it). If it cannot be created, HARD HALT with exit code 4 (write-failure): display "Quick Skill cannot start: the run folder could not be created. {the first stderr line}" and emit with nothing to stage in:uv run {emitEnvelopeHelper} emit-halt --workflow skf-quick-skill --target stderr <<'SKF_JSON' {"phase": "on-activation", "halt_reason": "write-failure", "reason": "<that message, one line>", "skill_package": null} SKF_JSONWith no emitter path (an incomplete install), each halt displays its message alone and step 6 §3 writes no result contract.
- Resolve
{headless_mode}: true if--headlessor-Hwas passed as an argument, or if{sidecar_path}/preferences.yamlsetsheadless_mode: true. Default: false. Resolve workflow customization. Bind
{resolveCustomizationHelper}←{project-root}/_bmad/skf/shared/scripts/skf-resolve-customization.py, else{project-root}/src/shared/scripts/skf-resolve-customization.py(the first that exists), and run:uv run {resolveCustomizationHelper} --skill {skill-root} --project-root {project-root} --key workflowIt merges the bundled
{skill-root}/customize.tomlwith{project-root}/_bmad/custom/skf-quick-skill.toml(team overrides, committed) and.user.toml(personal overrides, gitignored). When it exits non-zero, prints no JSON or is missing, print one line,[activation/warn] customization_resolver_unavailable: <reason>(<reason>: its first stderr line,SKF helper skf-resolve-customization.py not foundwhen the script is missing,no JSONwhen it printed none). If the resolver cannot run, read{skill-root}/customize.tomlalone and use its bundled defaults: the{project-root}/_bmad/custom/overrides do not apply to this run. In that case keep the reason as{customization_resolver_unavailable}(unset when the resolver ran) and, when{emitEnvelopeHelper}has a path, record it in the run sink: writecustomization_resolver_unavailable: {customization_resolver_unavailable}to{run_dir}/resolver-warning.txtwith a file write, neverecho(the reason can hold quotes or$( )), then runuv run {emitEnvelopeHelper} record --run-dir "{run_dir}" --warning "$(cat "{run_dir}/resolver-warning.txt")". Under--batch,references/batch-mode.md§2 records that file in each target's run folder.Bind these three as workflow-context variables, taking the default when the merged value is empty or absent:
{skillTemplatePath}←workflow.skill_template_path, elseassets/skill-template.md{batchOutputPath}←workflow.batch_output_path, else{skills_output_folder}/_batch/{onCompleteCommand}←workflow.on_complete, else empty (step 6 §3 then runs no hook)
Run each
workflow.activation_steps_prependentry now, in order. Hold everyworkflow.persistent_factsentry as standing context for the whole run; afile:entry loads the contents of the paths or globs it names: the bundled default loads everyproject-context.mdunder{project-root}; an entry prefixed!drops each earlier entry it names and loads nothing itself, so an override's"!file:{project-root}/**/project-context.md"turns that default off. Once step 4 has parsed the flags, before step 5 or 6 starts the run, run eachworkflow.activation_steps_appendentry in order.Parse CLI overrides into the workflow context as
{overrides}:Flag Effect --language-hint <lang>Sets language_hint: step 1 §4 takes it as the language, with no detection and no multi-language gate, and step 1 §3 asks only that language's registry.--scope-hint <path>Sets scope_hint: the folder step 3 reads the entry points and skill folders from.--description "<string>"Replaces the extracted description in step 4 §2, which checks its length and voice as it checks an extracted one. --exports "<name1,name2,...>"Replaces the extracted export list in step 4 §2: comma-separated, each name trimmed, empty items skipped. --skip-snippetNo context-snippet.md: step 4 §3 and step 5 §2 skip it. --no-active-pointerStep 6 §1 leaves {skill_group}/activeas it is.--batch <file>Compiles every target the file lists, headless (On Activation step 5); --skip-snippetand--no-active-pointerapply to every target in the batch.--fail-fastWith --batch: the batch stops at the first failed target.--language-hint,--scope-hint,--descriptionand--exportsare single-target flags: batch mode refuses them.- If
--batchis set, load and readreferences/batch-mode.mdin full before anything else and follow it. - Load, read the full file, and then execute
references/resolve-target.mdto begin the workflow; when{headless_mode}is true, print step 1'sstartevent first (references/halt-contract.md). In batch mode,references/batch-mode.mdloads it for each target instead.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

