Project Brief
Read-only workspace-level synthesis of project outcomes, requirement linkage, delivery evidence, coordination risks, and the single most important next coordination action.
Install
npx skills add flurdy/agent-skills --skill project-briefgit clone --depth 1 https://github.com/flurdy/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/project-brief ~/.claude/skills/project-briefPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Project Brief — Workspace Coordination Synthesis Answer one bounded question: > What coordination action is most necessary now to keep this workspace's stated outcomes achievable? Produce a concise, read-only brief from current evidence. Do not become another project tracker, change source systems, post updates, drive releases, or infer authority that was not recorded. ## Usage ```text /project-brief ``` Version 1 accepts no modes, target identifiers, arbitrary JQL, or configuration file. Run it from a validated `project-workspace` root. If the current directory is not an unambiguous workspace root, stop and ask for the correct root; never widen scope to the user's whole Jira portfolio or GitHub organisation. ## Relationship to adjacent skills Keep this skill at synthesis depth and delegate source-specific investigation: - **`/landscape`** — session orientation and immediate working-copy action. - **`/tracking-sweep`** — portfolio-wide Jira, Beads, and PR drift. - **`/outstanding-work`** — completion evidence for one ticket. - **`/backlog-groom`** — backlog quality and lifecycle hygiene. - **`/pr-status`** — full PR, CI, approval, and review-thread details. - **`/release-status`** — project-specific release and rollout state. - **`/architect`** — architecture and implementation planning. - **`/triage`** — create or split durable work. Do not reproduce those skills' deep checks. Cite the relevant skill when the brief identifies a gap that needs investigation.
Details
- Skill name
project-brief- Repository
- flurdy/agent-skills
- Path
skills/project-brief/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Project Brief skill do?
Read-only workspace-level synthesis of project outcomes, requirement linkage, delivery evidence, coordination risks, and the single most important next coordination action.
How do I install the Project Brief skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add flurdy/agent-skills --skill project-brief. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Project Brief popular?
It lives in flurdy/agent-skills, which has 9 GitHub stars and 0 forks.
Related skills
Architect
9flurdy/agent-skills
Architecture and implementation planning gate for complex or high-blast-radius work. Produces evidence-backed decisions, reviewable slices, acceptance evidence, and conditional human review ownership without editing code.
Artifact Hygiene
9flurdy/agent-skills
Run a local-only, read-only advisory audit of publishable working-tree files and unpublished branch history with redaction-safe findings.
Backlog Groom
9flurdy/agent-skills
Auto-detects workspace unfinished backlogs across unique stores; otherwise local open beads. Flags thin prose, missing labels, drift, lifecycle and duplicates. Report-only; mutations need approval, destructive ones individually.
Reassess
9flurdy/agent-skills
Explicit read-only project reassessment. Compare intended outcomes, implementation, unfinished work, interrupted artifacts and revision-qualified build evidence; propose what to keep, update, add or retire without acting.
Pickup
9flurdy/agent-skills
Read-only shortlist of unassigned, ready Jira tickets your team could pick up next — active sprint first, then the next sprint and top of backlog — with flagged or blocked ones listed separately. Scoped by a workspace pickup.toml.
Release Maintenance
9flurdy/agent-skills
Separately confirmed manifest reconciliation, scoped config synchronization, workload restart, or evidence-backed rollout acknowledgement. Requires explicit invocation; never runs inside a release watch tick.
Browse the most popular Claude skills, all other skills, or write your own with the skills generator.