philoserf/skills/use-discipline
skills/use-discipline/SKILL.md
Primes the conversation for deep, not-yet-well-defined work by framing the arc — problem framing, brainstorming, planning, execution under rules, review via existing skills. Takes an optional topic argument to seed the problem space. Use to opt into disciplined multi-phase work rather than letting ceremony be always-on.
$ install --global
skillsauthnpx skillsauth add philoserf/claude-code-setup skills/use-disciplineInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 5:08 AM52.0s1 file scanned
SKILL.md
- description:
- Primes the conversation for deep, not-yet-well-defined work by framing the arc — problem framing, brainstorming, planning, execution under rules, review via existing skills. Takes an optional topic argument to seed the problem space. Use to opt into disciplined multi-phase work rather than letting ceremony be always-on.
- argument-hint:
- [topic]
Use Discipline
Single opt-in entry point for deep work. Replaces the always-on ceremony of auto-injected meta-skills with an explicit primer the user invokes when they want it.
Invocation
/use-discipline <topic>— frames the arc around the given topic and starts dig-and-advise/use-discipline(no argument) — ask "what are we working on?" and start dig-and-advise from the answer
Never error on missing argument. The conversation is the input.
The arc
This skill describes the arc. It does not enforce it. Phase transitions are conversational — suggest, wait, confirm, invoke. Never force.
- Frame — understand the problem space through dig-and-advise. Research tradeoffs, present 2-3 options with a clear recommendation, wait for direction. Lead with the durable option, not the expedient one.
- Brainstorm — when framing has converged enough to start exploring design, suggest moving to the
brainstormingskill. On confirmation, invoke it. - Plan — when a design is approved, suggest moving to the
writing-plansskill. On confirmation, invoke it. - Execute — after the plan is written, this skill exits. Execution is governed by the rules in
rules/(verification, testing, debugging, parallelism, code-review, test-failures) — not by this skill. - Review — post-execution review happens via existing local skills:
diff-reviewfor change-level cleanupvc-shipfor branch finishing (atomic commits, PR)session-reviewfor retrospective
This skill does not orchestrate review.
Not a state machine
The user can skip framing and go straight to planning, or skip brainstorming if the design is already clear. The arc is a menu, not a pipeline. If the work turns out not to need this much discipline, exit early and just do it.
What this skill does not do
- No ALL-CAPS directives
- No session-start injection (opt-in only)
- No TodoWrite per phase — phases are conversational, not tracked tasks
- No hard gates between phases
- No auto-committed artifacts (brainstorming outputs live in conversation; plans live in
~/.claude/scratch/plans/)
Voice
Model the terse, dig-and-advise tone the arc encourages. Ask one question at a time. Prefer multiple choice. Lead with recommendations. Wait for approval before acting on anything non-trivial.
Do not use when
- Already know which phase you are in — invoke that skill directly (
brainstorming,writing-plans) - The work is well-defined and short — just execute without the arc
- Running end-of-change cleanup — use
diff-review
Related Skills
philoserf/skill-cleaner
testing
VerifiedTrustedCommunity
Audits ~/.claude/skills/ for unused entries, duplicate names, missing descriptions, and the longest descriptions. Use when trimming the user-level skill set, asking which skills are unused, finding duplicates, or auditing skill hygiene.
12SKILL.mdUpdated Jun 3, 2026
philoserf/skills/flowershow-cli
tools
VerifiedTrustedCommunity
Publishes and manages Flowershow sites with the `fl` CLI (the Go-based successor to the deprecated `@flowershow/publish` npm package). Use when publishing a note or folder to Flowershow, syncing updates to an existing site, managing auth, listing or deleting sites, or installing/upgrading the CLI.
12SKILL.mdUpdated Jun 3, 2026
philoserf/editor
tools
VerifiedTrustedCommunity
Copy edits prose while preserving voice and register. Use when asked to edit, copy edit, line edit, proofread, revise, polish, tighten, rewrite, or clean up essays, articles, drafts, or fiction. Flags wordiness, passive voice, clichés, hedging, and nominalizations with bracket markup or clean rewrites.
12SKILL.mdUpdated May 26, 2026
philoserf/skills/claudemd-capture
tools
VerifiedTrustedCommunity
Improves CLAUDE.md by analyzing conversation patterns. Use when Claude keeps repeating a mistake, when teaching a new preference, or when consolidating guidance from repeated instructions. Captures recurring corrections and style preferences into project instructions.
12SKILL.mdUpdated May 24, 2026