osdlc
@osdlc Organization
Public Skills
skill-review
by osdlc
Review one skill or every skill in a plugin against the skill-author checks and against each other, and recommend what to tighten, map, merge, split, retire or document. Read-only; with --fix it hands each marked skill to skill-author.
import-planning
by osdlc
Walk a project root for planning-shaped prose (READMEs with roadmap sections, brain-dump notes, dated checklists, issue archives, etc.) and produce draft task/milestone entities under docs/planning/, so a project can adopt the SDLC plugin without re-keying its prior planning history. Spins up a fresh worktree, runs a deterministic scanner, dispatches one sub-agent per candidate to interpret it, presents a batched plan for one-shot approval, then shells out to sdlc task create / sdlc milestone create and Edits the drafted body sections in. Opens a PR at the end. Pass --auto to skip the confirmation prompt, --dry-run to stop at the plan, --scope <path> to restrict the scan.
skill-author
by osdlc
Write or tighten a minimal skill: one process, a scope line, inputs and outputs, numbered steps, and optionally a map, grading checks and a test environment. Short, lists over prose, other skills called by wikilink. Script-free unless a step is deterministic and repeated. Use it for every new skill in craft or sdlc.
import-planning
by osdlc
Walk a project root for planning-shaped prose (READMEs with roadmap sections, brain-dump notes, dated checklists, issue archives, etc.) and produce draft task/milestone entities under docs/planning/, so a project can adopt the SDLC plugin without re-keying its prior planning history. Spins up a fresh worktree, runs a deterministic scanner, dispatches one sub-agent per candidate to interpret it, presents a batched plan for one-shot approval, then shells out to sdlc task create / sdlc milestone create and Edits the drafted body sections in. Opens a PR at the end. Pass --auto to skip the confirmation prompt, --dry-run to stop at the plan, --scope <path> to restrict the scan.
capability-map
by osdlc
Map out the capability graph for one scope of the project: survey the code (or the product's capability-map table), propose new Capability entities where the map has gaps, enrich existing ones with locations, grain, audience and related links, and report retire candidates. Runs sdlc capability coverage and sdlc capability graph read-only, dispatches one read-only sub-agent per candidate, renders one batched plan for approval, then writes through sdlc capability create / sdlc capability update and opens a PR. Invoke when capabilities are missing, ungraded, unanchored, or when the System page's capability view looks empty for an area. Usage: /sdlc:capability-map <dir C-NNNN areas> [--dry-run] [--auto].
pr-stats
by osdlc
Summarize a pull request or branch diff beyond GitHub's +/-: lines added and removed by code, comments, blank and prose; a change-category breakdown (added, deleted, renamed, tests, docs, generated, formatting-only, comment-only, logic); dependency and exported-API changes; and the cyclomatic-complexity movers. Use before or after opening a PR, in review, or when asked to "summarize this change", "how big is this PR", "what did this branch actually change", or "add stats to the PR". Optionally writes the table into the PR body. Runs from a bundled script with plain Node, git and gh; needs no other plugin.
explain
by osdlc
Explain one thing as a parley document with no questions: the subject as typed blocks with numbered nodes anchored to the exact text, a walkthrough the reader comments on. Domains are notes beside this skill (sql today). Then hand it to parley. Use it when the reader needs to understand something, not decide something.
lib-publish-ready
by osdlc
Audit one library package for a first public release. Produces a readiness report (every quality-bar row with evidence and a verdict: pass, gap, blocker, n/a or owner), the evidence for the name, worthwhile, stable, home and API gates, an inventory of the public API, the first public version, a sanitized CHANGELOG draft, owner questions with a recommendation each, and a fix list whose items are tagged safe or needs-decision. Reads the package; never writes inside it. Use it before publishing a library to a public registry such as crates.io or npm, or to re-audit after fixes.
explore-codebase
by osdlc
Systematic method for understanding an unfamiliar codebase: getting oriented in a new repo, locating where something is implemented, tracing how a feature or request flows end to end, and building an accurate mental model before answering questions or making changes. Use whenever you're dropped into a repo or the user asks things like "how does X work here", "where is Y handled", "how is this project structured", "help me understand this codebase", "onboard me to this code", "find where Z is implemented", or "explore this repo and write up notes" — or before editing code you haven't read yet. Can optionally save the resulting map as a markdown file, a linked Obsidian-style vault, or a self-contained HTML page carrying diagrams of the structure it found.
spawn-task-pr
by osdlc
Open a PR carrying a single scaffolded follow-up task file on a target repo. /sdlc:task-work Step 8 runs the spawn-from-post-mortem procedure, whose step 4 dispatches one invocation per classified friction bullet, so each follow-up lands as its own PR. Upstream-plugin / Cross-project-request bullets target the resolved foreign repo; Local bullets target this repo. Idempotent and non-interactive: takes the target-repo path, slug, headline, classification, and tag; reuses or creates a worktree on that repo; branches from origin/main (--target-base default main, --target-remote default origin); scaffolds the task via sdlc task create at the fallback status (default planning/draft); optionally drives it to open/ready via auto-define + ensure-ready when --drive-to-ready is set; commits on --branch (default meta-task/<slug>); pushes; and per --pr either opens a fresh PR or appends to that branch's open rolling PR. Emits a deterministic stdout marker. --no-push rehearses without pushing or opening a PR.
research
by osdlc
Answer one question with sourced findings inside a time box: state the question, search the repo before the web, record each source with what it settles, and end with findings, open points and a recommendation. Use it whenever a decision or a capability needs facts first.
explore-codebase
by osdlc
Systematic method for understanding an unfamiliar codebase: getting oriented in a new repo, locating where something is implemented, tracing how a feature or request flows end to end, and building an accurate mental model before answering questions or making changes. Use whenever you're dropped into a repo or the user asks things like "how does X work here", "where is Y handled", "how is this project structured", "help me understand this codebase", "onboard me to this code", "find where Z is implemented", or "explore this repo and write up notes" — or before editing code you haven't read yet. Can optionally save the resulting map as a markdown file, a linked Obsidian-style vault, or a self-contained HTML page carrying diagrams of the structure it found.
capability-review
by osdlc
Review existing Capability entities for accuracy against the code they anchor: do the locations still realize the Statement, do kind, audience and state match the shared rubric, do parent_key and related still resolve, does the body describe what the code does. Runs sdlc capability coverage and sdlc capability graph read-only, dispatches one read-only sub-agent per capability, and prints a report. With --fix it also corrects frontmatter through sdlc capability update and stamps last_reviewed; with --rewrite it also rewrites drifted body sections; both open a PR. Invoke after a mapping run, after a refactor that moved packages, or when the System page's capability view looks wrong. Usage: /sdlc:capability-review <dir C-NNNN all> [--fix] [--rewrite] [--auto].
capability-groom
by osdlc
Take a capability from a name to a chosen shape and implementation architecture: define it, research prior art and constraints, propose two or three shapes, select one with stated criteria, and leave a capability entry and a decision ready to record. Use it before any task is split from a capability.
task-auto-define
by osdlc
Drive one or more task documents toward the implementation-ready contract (solutions/ontological/lib/model/entities/task/implementation-ready.md) by synthesizing best-effort content from each task's existing prose plus codebase context, without prompting the user. Multiple tasks run in sequence, one commit and one slug-namespaced terminal marker each. --make-pr pushes the run's commits on a chore/ branch and opens a PR (default off — commit on the current branch only). Stamps a discoverable machine-authored marker on every synthesized spec. Never changes state: /sdlc:task-ensure-ready promotes to open/ready and stamps readiness_verified_at in one commit. Dispatched by /sdlc:task-ensure-ready when a task is autonomy: autonomous/pr and the deterministic verify reports a gap.
milestones-from-file
by osdlc
Given a filepath, do a best-effort extraction of milestone entities from that file (markdown notes, planning docs, brain-dump, anything). Creates one milestone file per extracted candidate via sdlc milestone create, all inside a fresh worktree, then opens a PR. Pass --auto to skip per-candidate confirmation.
decision-make
by osdlc
Make one decision in the open: state the question and its forcing drivers, research the facts and the prior art it rests on, write the options with consequences, choose with criteria written first, and record what would reopen it. Use it whenever a choice will constrain later work.
orchestrate
by osdlc
Run one deterministic orchestrate tick by invoking sdlc orchestrate run --once: dispatch ready tasks, classify and act on open PRs, and close out merged ones. Wrap with /loop /sdlc:orchestrate for the hands-off self-driving orchestrator loop.
bug-finder
by osdlc
Sweep an entire codebase for real bugs and fix them. Partitions the tree into module-boundary territories, then runs three chained agent workflows — scan (three altitudes: in-function, in-module, in-library) → adversarial validate → fix → verify-fix → land — so a fresh agent performs every step and the orchestrating session never reads source itself. Opens one PR per module boundary, then surveys the open PRs, computes the conflict matrix deterministically with git merge-tree, and merges the overlapping bugfix branches into each affected PR in a single aggregated push so CI runs once per PR, not once per fix. Pass --bomb for maximum parallelization.
capability-review
by osdlc
Review existing Capability entities for accuracy against the code they anchor: do the locations still realize the Statement, do kind, audience and state match the shared rubric, do parent_key and related still resolve, does the body describe what the code does. Runs sdlc capability coverage and sdlc capability graph read-only, dispatches one read-only sub-agent per capability, and prints a report. With --fix it also corrects frontmatter through sdlc capability update and stamps last_reviewed; with --rewrite it also rewrites drifted body sections; both open a PR. Invoke after a mapping run, after a refactor that moved packages, or when the System page's capability view looks wrong. Usage: /sdlc:capability-review <dir C-NNNN all> [--fix] [--rewrite] [--auto].
entities-migrate
by osdlc
Apply mechanical, auto-fixable schema drift to entity instances under docs/planning/<plural>/. Spins up a worktree, runs the audit, applies every fix the audit flagged auto_fixable — stamping the missing schema_version into frontmatter AND running the deterministic body transforms (the v_n->v_n+1 chain that reshapes body sections, e.g. a task's bulleted Files-to-touch/Today blocks into typed v3 tables) — and opens a PR. Body transforms are deterministic TS that reshape what's unambiguous and flag the ambiguous tail (definition_gap + status downshift, mid-flight preserved); no LLM in the migrate path. Skips closed entities by default; pass --include-closed to forward that flag to the audit and treat closed entities like active ones.
explain
by osdlc
Explain one thing as a parley document with no questions: the subject as typed blocks with numbered nodes anchored to the exact text, a walkthrough the reader comments on. Domains are notes beside this skill (sql today). Then hand it to parley. Use it when the reader needs to understand something, not decide something.
collaborate
by osdlc
Co-edit a markdown document the user has open and is typing in. Read the document, find @agent markers, do the work each one asks for, then present every proposed change in chat and get approval before writing anything. Use when the user points at a markdown file containing @agent markers, asks you to fill in or answer parts of a doc you are both working on, or says to collaborate on / work through a document together. Exists to keep writes from clobbering content the user is editing live.
pr-review
by osdlc
Run an adversarial code review of an open pull request's diff and post the findings as a PR comment. Given a PR number, fetches the diff via gh, judges it against the project's configured rubric (orchestrator.review.rubric_path in sdlc.yaml; falls back to a generic inlined rubric when unset), and posts a summary comment through the same self-posted-comment wrapper /sdlc:pr-respond uses, so the orchestrator's own comment cursor filters it out on the next /sdlc:pr-check tick. Read-only on the repo (no commits, no code changes, no worktree needed) — the posted comment is its only write. This is the sdlc chain's review-stage workflow ([[D-0019-sdlc-chain-stages-and-labels]]); the prs orchestrator tick dispatches it for a PR it has never classified before (merges never dispatches pr-review — only pr-respond, for a merge conflict), under the model workflows.pr-review.profile or .model names.