Skip to main content

cyberuni/cyber-sdd

SkillsMP has collected 79 skills from cyberuni/cyber-sdd. Open a skill to review its source and details.

Latest recorded source activity
SkillsMP catalog refreshed
skills collected
79
GitHub stars
1
GitHub forks
0

Skills in this repository

classification pending

Showing 40 of 79 collected skills.

occupation
unclassified
description

Detect and reconcile prose-suite drift across the SDD project spec's nodes — the on-demand, CI-usable complement to the inline spec-gate check; use for corpus audits, post-large-change verification, or CI gating.

updated
occupation
unclassified
description

Use this skill when running ACED evals to score agent configuration behavior against its frozen .feature suite — after editing a skill, AGENTS.md section, subagent, or command.

updated
occupation
unclassified
description

Use this skill when comparing two versions of an agent configuration to detect regressions or confirm improvements before committing a change.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — project-spec/check-spec-references' engine that resolves every relative reference in one project spec's markdown and fails on the ones pointing at nothing — run from the per-project CI entrypoint, not triggered by users…

updated
occupation
unclassified
description

Partial Skill: invoke by name only — project-spec/check-project-specs' engine that runs every project-spec check against the one spec governing the invoking package — the per-project CI entrypoint, not triggered by users directly.

updated
occupation
unclassified
description

Use this skill when the user wants to create or improve a command — a user-invoked-only slash workflow (`/name`) that never auto-triggers from the model. Trigger on "create a command", "add a slash command", "make a /deploy command", "add a user-only…

updated
occupation
unclassified
description

Use this skill when the user wants to create, scaffold, or formalize a workflow skill — a process, tool-based, or standard SKILL.md — from scratch or from an existing ad-hoc workflow. Trigger on "create a skill", "write a skill for X", "I want a skill that…",…

updated
occupation
unclassified
description

Audit, improve, or write a SKILL.md — check description trigger coverage, structure, security, and agentskills.io compliance. Use when reviewing or creating a skill for Claude Code, Cursor, Codex, Copilot CLI, or any agentskills-compatible runtime, even if…

updated
occupation
unclassified
description

Use this skill when generalizing what the current session actually did into a reusable SKILL.md — "skillify this", "turn what we just did into a skill", "make this reusable". Not for scaffolding a skill from scratch (define-skill), extracting the session into…

updated
occupation
unclassified
description

Use this skill to make a change to an SDD project — triggered by a general change request like "add a start-mission skill to sdd", "implement the auth capability", "revise the gateway spec", or "work on <github issue url>". Opens a change request against the…

updated
occupation
unclassified
description

Partial Skill: invoke by name only — the ACED eval-result freshness check — decides whether a recorded result still describes the configuration on disk, not user-triggered.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — corpus/discovery's frontmatter-scanning engine across the SDD spec locations — used by the sdd gateway to scan statuses and by start-mission to locate the project spec, not triggered by users directly.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — the SDD default spec-producer procedure. Loaded in-session by the conductor when it runs the spec-producer role inline, not user-triggered.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — blast-estimate's engine that computes a Mission's blast (low/medium/high) from its touch-set plus the project corpus and lines it up against the hand-typed declared blast — the engine for the blast-estimate node, consumed…

updated
occupation
unclassified
description

Partial Skill: invoke by name only — project-spec/partition-quality's engine: measures from git history how much parallel work a layout permits, and compares candidate layouts. Opt-in from scaffold-project-spec and the formation loop, and runnable standalone;…

updated
occupation
unclassified
description

Partial Skill: invoke by name only — plan-brief/check-plan-safety's guard engine against machine-local path leaks in tracked plan artifacts — the CI guard, not triggered by users directly.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — retired-terms' guard engine against survivors of a retired path, directory, or naming convention across the whole tracked corpus — the CI guard, not triggered by users directly.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — project-spec/scenario-overlap's engine that detects the same behavior specified in two nodes' suites across one project spec — feeds the formation Warden, not triggered by users directly.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — project-spec/check-spec-structure's engine that audits a project spec's internal node-shape — feeds the formation Warden, not triggered by users directly.

updated
occupation
unclassified
description

Internal skill: at a known node-level collision between two missions, descends the finer-than-node ladder (file → region → semantic) to classify the clash hard or soft — a read-only downgrade-only disambiguator, not triggered by users directly.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — project-spec/concept-index's engine that derives the by-concept view of a project spec into spec.md — used to re-unify a cross-cutting concern the capability folder tree scatters, not triggered by users directly.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — intake/plan-discovery's engine that surfaces resumable mission plan briefs — used by the sdd gateway on entry, not triggered by users directly.

updated
occupation
unclassified
description

Use this skill to onboard SDD's opt-in repo-scoped conveniences — currently the mission statusline, which surfaces the current mission phase in the Claude Code status line while a mission runs. Trigger on "set up the statusline", "configure the SDD status…

updated
occupation
unclassified
description

Partial Skill: invoke by name only — intake/manage-ignore's curation engine for the SDD ignore rules — loaded by the manage gateway (Housekeeping), not triggered by users directly.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — the curation engine for a project's scenario-bridge.toml — loaded by the manage gateway (Setup & discovery), not triggered by users directly.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — corpus/spec-anchors' curation engine for SDD's extra spec-discovery anchors — loaded by the manage gateway (Housekeeping), not triggered by users directly.

updated
occupation
unclassified
description

Internal skill: the mission-graph kernel — a git-tracked, append-only work-graph store folded into a ready frontier and a cycles repair view; used by the cyberfleet-batch dispatch loop, not triggered by users directly.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — project-spec/place-node's engine that suggests a capability home and surfaces duplicates for a new node — used by explore, not triggered by users directly.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — the SDD Doctrine loop's last retro step — the gated, idempotent tracked deletion of a retired mission plan. Invoked by the doctrine-loop Scanner, not user-triggered; the clearance contract lives in the body + README.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — the SDD governance matcher, resolving which actor-bar governances apply to a touched file — run by the conductor and the cold spec/impl judges, not triggered by users directly.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — intake/resolve-tracking's engine that resolves an artifact's tracked-or-ignored signal — run by the conductor at intake, not triggered by users directly.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — the SDD spec gate (Draft → Approved), the verdict on a CR's spec + suite diff — run by the conductor inside the mission loop, not triggered by users directly.

updated
occupation
unclassified
description

Internal skill: reconciles a Mission's declared touch-set against what its git diff actually changed — read-only, post-hoc; used to correct the mission-graph's hazard set from prediction to reality, not triggered by users directly.

updated
occupation
unclassified
description

Partial Skill: invoke by name only — the Gherkin-scenario-to-test-report bridge verifier — invoked by the impl-judge at the impl gate, not triggered by users directly.

updated
occupation
unclassified
description

Use this skill when contributing local improvements to an installed skill back to its source repo via PR.

updated
occupation
unclassified
description

Use this skill to register ACED as the SDD plugin for agent-configuration domains — writes an aced role-map entry to .agents/universal-plugin.json so the conductor resolves the ACED production-chain roles for skills, subagents, commands, and AGENTS.md…

updated
Showing 40 of 79 collected skills.