SDD Capabilities
Fills implementation, actions and review in specs/capabilities.yml from what the environment
actually offers, then asks the user to confirm or correct every choice. Keys and defaults: references/capabilities.md.
Nothing is written before the user has confirmed the draft.
$ARGUMENTS limits the run to one section (implementation, actions, review); empty → all three.
Start with a task list (load, discover, draft, confirm, write, re-check) and keep it current.
1. Load
specs/capabilities.yml missing → STOP: "Run /sdd:doctor init first." (also when only the old
specs/capabilities.md exists: init migrates it).
- Read it whole. Note each project from
projects (name, kind, stack) and the current value of
every key: a non-default value is a decision the user already made — show it as such in the draft
and change it only when they say so.
specs/constitution.md §2 gives the project's check commands; they tell you what exists to verify with.
2. Discover what is available
Collect candidates; read-only.
- This session: the skills and agents the session lists (Skill tool listing, Agent tool
subagent_types). Use the exact names, including a plugin prefix (git-workflow:create-commit).
- Installed plugins, including disabled ones and ones installed before:
claude plugin list
(fall back to ~/.claude/plugins/installed_plugins.json). For each, read its skills/*/SKILL.md and
agents/*.md frontmatter name and description under the install path. Mark a candidate
installed, not enabled in this session when it is not in the session listing — it cannot be
used until the user enables it.
- User and project files:
~/.claude/skills, ~/.claude/agents, .claude/skills, .claude/agents
(frontmatter only).
- Repository signals:
gh auth status and a GitHub origin (can the session open PRs), CI config
(.github/workflows, …), an e2e or UI test setup (Playwright, Cypress, Maestro, Detox …), a dev
command in constitution §2 (the app can be started for a QA check).
Match by description, not by name alone, and per project stack:
| Section |
Look for |
implementation |
an agent or skill that writes code for the project's stack (a *-developer, *-engineer, a frontend/backend expert). Not reviewers, testers, planners |
actions |
skills/agents that create a branch, a commit, a pull request |
review audit flow |
skills/agents that audit code for the stack (accessibility, performance, security, framework rules) |
review.checks |
an agent that runs the app and tests behaviour (QA, e2e); only when the app can be started |
A candidate that fits more than one project's stack is offered per project; one that fits none is dropped.
3. Draft
For each section build a proposal with a one-line reason per value, and mark confidence:
- Clear — exactly one fitting candidate, or the current value stays.
- Choice — several candidates fit; list them, recommend one.
- Gap — nothing fits, or the choice depends on how the team works.
Defaults are valid answers: no fitting implementer → default: in-session; no git-action tooling →
leave actions.branch / commit / pr at null; never invent a name that was not discovered.
Show the whole draft as one YAML block — the keys exactly as they would be written, each with
its reason beneath as a comment — and say which candidates were found but are not enabled.
4. Confirm and fill the gaps
Ask with AskUserQuestion, not free text. The question must stand alone (name the section and the
proposed lines).
- One confirmation first: "Is this draft correct?" — Yes, write it / Change something.
- If Change something, or any value is a Choice or Gap, ask one question per section
that needs it (up to four per call), options being the discovered candidates, the recommended
one first, plus the default (
in-session / unset). Examples of gaps worth asking:
- several implementers fit one project, or none fits and the user may have one outside the
scan (ask for its name, then check it exists);
- whether
publish should be ask or off, and whether tests may be skip;
implementation.isolation: none (this session implements and commits each task) or
worktree: (a sub-session, worktree and branch per task). Ask merge (pr / auto) and
parallel only after the user chose worktree:; they go under it;
- whether a QA/e2e
review.checks entry should run on every review, given what it costs;
- a project with no check commands in constitution §2 — say that
tests: run has nothing to run there;
- a candidate that is installed but not enabled — enable it first, or leave it out.
- Ask only what the scan cannot settle; a Clear value is not re-asked unless the user chose
Change something. After the answers, show the final lines once more only if they differ from
the confirmed draft.
5. Write
- Edit only the values under
implementation, actions and review; keep the comments, format,
projects, generated and every line the user did not change byte-for-byte. A section missing
from the file is added from the template in its usual order. Two-space indentation; quote a key or
value that starts with @ (npm scopes) or another YAML indicator.
- One value per key, grammar exactly as in the reference (
skill:<name>, agent:<name>,
command:<shell>, in-session; per project under implementation.projects / review.projects,
<project>: <value>; review.checks as a list). Unknown keys stay untouched, and so does
review.ci unless the user asked: it is about CI, not about who does a step.
- Print one line per section: changed / unchanged.
6. Re-check
Run mcp__sdd__doctor_check (tool missing → say the check was skipped) and report any finding on
capabilities. Finish with the next step: /sdd:spec feat <description> when ready, otherwise
/sdd:doctor init. Mention that re-running /sdd:capabilities after installing plugins refreshes the choices.
1---2name: capabilities3description: Configure specs/capabilities.yml — who implements tasks, who runs branch/commit/PR, how /sdd:review verifies — from the skills, agents and plugins you have installed, then confirm each choice with you4allowed-tools: Bash, Read, Edit, Glob, Grep, AskUserQuestion, mcp__sdd__doctor_check5argument-hint: "(optional: implementation | actions | review)"6disable-model-invocation: true7metadata:8 source: https://skillmd.com/skills/janszewczyk/capabilities9---1011# SDD Capabilities1213Fills `implementation`, `actions` and `review` in `specs/capabilities.yml` from what the environment14actually offers, then asks the user to confirm or correct every choice. Keys and defaults: [references/capabilities.md](${CLAUDE_PLUGIN_ROOT}/references/capabilities.md).15Nothing is written before the user has confirmed the draft.1617`$ARGUMENTS` limits the run to one section (`implementation`, `actions`, `review`); empty → all three.18Start with a task list (load, discover, draft, confirm, write, re-check) and keep it current.1920## 1. Load2122- `specs/capabilities.yml` missing → STOP: "Run `/sdd:doctor init` first." (also when only the old23 `specs/capabilities.md` exists: `init` migrates it).24- Read it whole. Note each project from `projects` (name, kind, stack) and the current value of25 every key: a non-default value is a decision the user already made — show it as such in the draft26 and change it only when they say so.27- `specs/constitution.md` §2 gives the project's check commands; they tell you what exists to verify with.2829## 2. Discover what is available3031Collect candidates; read-only.3233- **This session:** the skills and agents the session lists (Skill tool listing, Agent tool34 `subagent_type`s). Use the exact names, including a plugin prefix (`git-workflow:create-commit`).35- **Installed plugins**, including disabled ones and ones installed before: `claude plugin list`36 (fall back to `~/.claude/plugins/installed_plugins.json`). For each, read its `skills/*/SKILL.md` and37 `agents/*.md` frontmatter `name` and `description` under the install path. Mark a candidate38 *installed, not enabled in this session* when it is not in the session listing — it cannot be39 used until the user enables it.40- **User and project files:** `~/.claude/skills`, `~/.claude/agents`, `.claude/skills`, `.claude/agents`41 (frontmatter only).42- **Repository signals:** `gh auth status` and a GitHub `origin` (can the session open PRs), CI config43 (`.github/workflows`, …), an e2e or UI test setup (Playwright, Cypress, Maestro, Detox …), a dev44 command in constitution §2 (the app can be started for a QA check).4546Match by description, not by name alone, and per project stack:4748| Section | Look for |49|---|---|50| `implementation` | an agent or skill that **writes code** for the project's stack (a `*-developer`, `*-engineer`, a frontend/backend expert). Not reviewers, testers, planners |51| `actions` | skills/agents that create a branch, a commit, a pull request |52| `review` audit flow | skills/agents that **audit** code for the stack (accessibility, performance, security, framework rules) |53| `review.checks` | an agent that runs the app and tests behaviour (QA, e2e); only when the app can be started |5455A candidate that fits more than one project's stack is offered per project; one that fits none is dropped.5657## 3. Draft5859For each section build a proposal with a one-line reason per value, and mark confidence:6061- **Clear** — exactly one fitting candidate, or the current value stays.62- **Choice** — several candidates fit; list them, recommend one.63- **Gap** — nothing fits, or the choice depends on how the team works.6465Defaults are valid answers: no fitting implementer → `default: in-session`; no git-action tooling →66leave `actions.branch` / `commit` / `pr` at `null`; never invent a name that was not discovered.6768Show the whole draft as one YAML block — the keys exactly as they would be written, each with69its reason beneath as a comment — and say which candidates were found but are not enabled.7071## 4. Confirm and fill the gaps7273Ask with `AskUserQuestion`, not free text. The question must stand alone (name the section and the74proposed lines).75761. **One confirmation first:** "Is this draft correct?" — *Yes, write it* / *Change something*.772. If *Change something*, or any value is a **Choice** or **Gap**, ask one question per section78 that needs it (up to four per call), options being the discovered candidates, the recommended79 one first, plus the default (`in-session` / unset). Examples of gaps worth asking:80 - several implementers fit one project, or none fits and the user may have one outside the81 scan (ask for its name, then check it exists);82 - whether `publish` should be `ask` or `off`, and whether `tests` may be `skip`;83 - `implementation.isolation`: `none` (this session implements and commits each task) or84 `worktree:` (a sub-session, worktree and branch per task). Ask `merge` (`pr` / `auto`) and85 `parallel` only after the user chose `worktree:`; they go under it;86 - whether a QA/e2e `review.checks` entry should run on every review, given what it costs;87 - a project with no check commands in constitution §2 — say that `tests: run` has nothing to run there;88 - a candidate that is installed but not enabled — enable it first, or leave it out.893. Ask only what the scan cannot settle; a **Clear** value is not re-asked unless the user chose90 *Change something*. After the answers, show the final lines once more only if they differ from91 the confirmed draft.9293## 5. Write9495- Edit only the values under `implementation`, `actions` and `review`; keep the comments, `format`,96 `projects`, `generated` and every line the user did not change byte-for-byte. A section missing97 from the file is added from the template in its usual order. Two-space indentation; quote a key or98 value that starts with `@` (npm scopes) or another YAML indicator.99- One value per key, grammar exactly as in the reference (`skill:<name>`, `agent:<name>`,100 `command:<shell>`, `in-session`; per project under `implementation.projects` / `review.projects`,101 `<project>: <value>`; `review.checks` as a list). Unknown keys stay untouched, and so does102 `review.ci` unless the user asked: it is about CI, not about who does a step.103- Print one line per section: changed / unchanged.104105## 6. Re-check106107Run `mcp__sdd__doctor_check` (tool missing → say the check was skipped) and report any finding on108capabilities. Finish with the next step: `/sdd:spec feat <description>` when ready, otherwise109`/sdd:doctor init`. Mention that re-running `/sdd:capabilities` after installing plugins refreshes the choices.