Skip to content

GentBajko/capstone / skills/core

Internal to the capstone suite - carries the shared rules (references/) and scripts every capstone subcommand reads; it exists so npx-skills installs ship them alongside the command skills. Not meant to be invoked directly; when invoked anyway, run references/../scripts/help.sh and output its stdout verbatim.

FileKindSize
SKILL.mdskill md902 B
VERSIONother6 B
references/arch-craft.mdmarkdown6.6 KB
references/code-craft.mdmarkdown9.6 KB
references/core-authoring.mdmarkdown8.7 KB
references/core.mdmarkdown55.5 KB
references/dispatcher.mdmarkdown1.9 KB
references/interview.mdmarkdown17.5 KB
references/logic-craft.mdmarkdown9.5 KB
references/protocols/architecture.mdmarkdown12.2 KB
references/protocols/build.mdmarkdown10.5 KB
references/protocols/doctor.mdmarkdown9.3 KB
references/protocols/edges.mdmarkdown12.6 KB
references/protocols/feature.mdmarkdown5.3 KB
references/protocols/groom.mdmarkdown11.2 KB
references/protocols/implement.mdmarkdown15.2 KB
references/protocols/logic.mdmarkdown10.7 KB
references/protocols/map.mdmarkdown38.5 KB
references/protocols/mockup.mdmarkdown11.0 KB
references/protocols/plan.mdmarkdown9.3 KB
references/protocols/retro.mdmarkdown9.3 KB
references/protocols/review.mdmarkdown10.6 KB
references/protocols/stack.mdmarkdown8.8 KB
references/protocols/standards.mdmarkdown8.5 KB
references/protocols/start.mdmarkdown14.6 KB
references/protocols/uiux.mdmarkdown24.8 KB
references/schema.txtmarkdown11.9 KB
references/standards-inventory.mdmarkdown36.9 KB
references/style.mdmarkdown1.8 KB
references/topics.mdmarkdown21.2 KB
references/uiux-craft.mdmarkdown20.7 KB
references/uiux-inventory.mdmarkdown19.3 KB
scripts/help-hook.shexecutablescript1.5 KB
scripts/help.shexecutablescript6.4 KB
scripts/init-config.shexecutablescript16.3 KB
scripts/lint-sync.shscript133.5 KB
scripts/map-check.shexecutablescript52.8 KB

references/dispatcher.md

View on GitHub
# Capstone dispatcher - one entry point, many protocols

Read by harnesses whose entry point is a single context file
(GEMINI.md imports this file). Claude-family harnesses route via the
individual wrapper skills instead; both paths land on the same
protocol files.

1. Read `core.md` (same directory) first: hard rules, voice, and
   user config. Then `core-authoring.md`, unless the route below lands
   on `start` or `feature`, which route rather than write.
2. Route on the first argument. Ten command words are the whole
   surface: `map`, `edges`, `doctor`, `review`, `groom`, `plan`,
   `implement`, `feature`, `start`, `help`. Every other protocol is a
   stage one of them runs, reached as that command's second word.
   The reserved subcommand words - the commands
   `map`, `edges`, `doctor`, `review`,
   `groom`, `plan`, `implement`, `feature`, `start`, under
   `start` the stage words `mockup`,
   `logic`, `uiux`, `architecture`, `standards`, `stack`, `build`,
   and under `review` the word `retro` -
   each route to `protocols/<name>.md`: execute that one protocol
   exactly; behaviors live there, not here.
3. A subcommand word is reachable only after its command: `start
   mockup` runs `protocols/mockup.md` and `review retro` runs
   `protocols/retro.md`, while a bare `mockup` or `retro` is not a
   command and routes to `start` like any other unrecognized argument.
   `retro` is the one subcommand that is not a stage: it reads a
   finished session rather than the code, and it sits under `review`
   because a session ends under every command, not just the pipeline.
4. Exception: when invoked as `map`, topic names win over
   stage words: `map architecture` regenerates
   `01-architecture.md` and never starts the architecture interview.
   `start architecture` is the interview.
5. `help`: run `../scripts/help.sh` via bash and output its stdout
   verbatim; nothing else.
6. No argument at all → `protocols/start.md`, the bare-"capstone"
   entry.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall