projectstatus
Use when the user asks "what's the project status", "where are we", "what should I work on next", "what's left", "what's blocked", or wants a spec-progress…
Skill by miroo93
Chalk Labs
Need help deploying projectstatus?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/miroo93-projectstatus
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: devops
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/projectstatus
What's inside
- Skill name
projectstatus- Description
- Use when the user asks "what's the project status", "where are we", "what should I work on next", "what's left", "what's blocked", or wants a spec-progress snapshot and a ranked next-action recommendation. Reads the project's spec layer (tasks lists, milestone order, blockers) from the stack profile. Progress only — for CI/DB/deploy health use /projecthealth.
- License
- MIT
- Instructions
- 163 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# projectstatus — spec progress & what to work next
**Invoke as `/projectstatus`.**
## Overview
Reports how far the project's **spec-driven work** has progressed and recommends
**one** thing to work next. It reads the spec layer declared in the project's
**stack profile**, reports progress per milestone/feature, surfaces blockers, and
offers to start the top recommendation via the matching hand-off skill.
**Core principle:** the task checkboxes ARE the source of truth for progress.
Don't guess from git or memory; parse the boxes. **Blockers first, then milestone
order.**
**Scope:** spec/feature progress only. It does **not** check CI, the database,
deploys, or environment drift — that's the separate `/projecthealth` skill.
Read-only: never edit specs or tick boxes here.
## Load the stack profile first
Read the project's **stack profile**: `docs/stack.md` (preferred) or `sdd-stack.md`
at the repo root. From its **Spec / planning layer** section take:
- **Spec location glob** — where feature specs/tasks live (e.g. `specs/**/tasks.md`,
`docs/features/*.md`). If this is **`none`**, the project has no spec oracle: say so
and fall back to summarizing open PRs / TODOs / the issue tracker, then stop.
- **Spec tooling** — e.g. GitHub Spec-Kit (`.specify/`), plain markdown, or none.
When Spec-Kit is present, the hand-offs below defer to it via the dev-workflows
thin entry points (`/spec`, `/tasks`, `/implement`, `/analyze`).
- **Branch naming** — for context when recommending where work lands.
Also read the **Binding context files** (e.g. `CLAUDE.md`, a constitution/principles
file). A constitution — if the project has one — encodes the **gates** (e.g.
test-first, migrations-first) that constrain task order; honor them when ranking.
Everywhere this skill says **[SPEC GLOB]**, substitute the profile's spec location;
everywhere it says **[PROJECT CONTEXT]**, substitute a compact summary of the binding
context + conventions.
## When to Use
- "What's the project status / where are we / what's left / what's next?"
- "What's blocked?" / "What should I pick up?"
- Before starting a work session, to orient.
**When NOT to use:** checking deploy/CI/DB health (→ `/projecthealth`); actually
*doing* the work (→ the hand-off skills below); writing or re-scoping a spec
(→ `/spec`, `/tasks`).
## What to read
| Artifact | Where | Tells you |
|---|---|---|
| Milestones / features | the **[SPEC GLOB]** dirs, ordered (by numeric prefix if present) | the sequence of work |
| Task list | each spec's `tasks.md` (or equivalent) | `- [ ]`/`- [x]` progress, `## Phase N` grouping, `TXXX` items |
| Decisions | a `DECISIONS.md` / decision log if the project keeps one | resolved clarifications + open external dependencies |
| Gates | the constitution/principles file from the profile, if any | principles (test-first, additive-migrations, …) that gate task order |
| Spec / plan | each spec's `spec.md` / `plan.md` | context when a feature has **no** task list yet |
**Task line format (Spec-Kit style, adapt to the project's):** `- [ ] TXXX [P?] [USN]
Description (path)` — `[P]`=parallelizable, `[S]`=setup, `[F]`=foundational,
`[USN]`=user story, `[L]`=launch, `[POL]`=polish. Projects using plain-markdown
checklists just have `- [ ] description` — count those the same way.
## Procedure
1. **Scan progress.** For each spec under **[SPEC GLOB]** with a task list, count
done/todo boxes and find the **current phase** (first `## Phase` containing an
unchecked task) and the **next 1–3 unchecked tasks** in it. Note any spec with
**no task list** (not yet broken down).
2. **Detect blockers.** Scan unchecked task lines and the decision log for blocker
signals (see table). Classify each as **external** (needs a human — owner access,
third-party input, a clarification) vs **internal** (a `gated on TXXX` / `applied
only after …` dependency you can satisfy by doing the prerequisite task).
3. **Rank (blockers first, then milestone order):**
- Externally-blocked items → list as **⛔ Blocked (flag, don't recommend)**.
- Otherwise the **earliest** spec (lowest numeric prefix / declared order) with
*actionable* unchecked tasks is the current focus. Within it, respect phase order
and any **test-first gate** from the constitution (a `TEST … fail first` task
precedes its implementation task — recommend the test task, not the impl).
- Specs with **no task list** → next action is to generate one (`/tasks`).
4. **Report** (format below).
5. **Offer to start** the top recommendation via the matching hand-off skill.
### Blocker signals to grep for
`⛔`, `BLOCKED`, `block and flag`, `NEEDS CLARIFICATION`, `gated on`, `applied
only after`, `pending owner`, `open dependency`, `⚠️`.
### Mechanical scan (adapt the glob to the profile)
```bash
# Use POSIX [[:space:]], NOT \s — awk does not understand \s.
cd "$(git rev-parse --show-toplevel)"
# SPEC_GLOB_DIR comes from the stack profile's "Spec location glob" (dir part).
for d in specs/[0-9]*/; do # adapt: e.g. docs/features/*/
t="$d/tasks.md" # adapt: the profile's task filename
if [ ! -f "$t" ]; then echo "$d — NO task list (needs /tasks)"; continue; fi
done=$(grep -cE '^[[:space:]]*-[[:space:]]*\[[xX]\]' "$t")
todo=$(grep -cE '^[[:space:]]*-[[:space:]]*\[ \]' "$t")
total=$((done+todo)); pct=$(( total ? 100*done/total : 0 ))
# current phase = first "## Phase" heading that has an unchecked box below it
phase=$(awk '/^## Phase/{p=$0} /^[[:space:]]*-[[:space:]]*\[ \]/{print p; exit}' "$t")
printf "%-34s %2d/%-3d (%3d%%) %s\n" "$d" "$done" "$total" "$pct" "${phase:-ALL DONE}"
done
# Blocked items across all specs:
grep -rnE '^[[:space:]]*-[[:space:]]*\[ \].*(⛔|BLOCKED|block and flag|NEEDS CLARIFICATION|gated on|applied only after|pending owner|open dependency|⚠️)' specs/[0-9]*/tasks.md
```
## Output format
```
## 📊 Project status — spec progress
| Milestone / feature | Progress | Status |
|---|---|---|
| 000 scaffold | 33/36 (92%) | 3 ⛔ blocked (owner access) |
| 001 auth | 32/54 (59%) | ▶ in progress — Phase 5 |From miroo93/dev-workflows, MIT.
More from miroo93/dev-workflows
- 0.474score
pr
miroo93
Use when you have follow-up changes to get onto a pull request, when updating a PR after main moved on, when a PR has conflicts with its base, or when you are…
SkillCFreshness: CClaude Code +9 - 0.474score
projecthealth
miroo93
Use when the user asks "is the project healthy", "is CI green", "what's red", "are we deployable", "any failing checks", "is anything broken"…
SkillCFreshness: CClaude Code +9 - 0.471score
e2e-smoke
miroo93
Internal skill invoked by /feature, /improve, /troubleshoot to run a local real-browser smoke check against the running app and return PASS/FAIL/BLOCKED.
SkillCFreshness: CClaude Code +9 - 0.470score
troubleshoot
miroo93
Use when you (the human) found a bug while manually testing the app — an agent-built feature shows a wrong value, broken interaction, or console/runtime error…
SkillCFreshness: CClaude Code +9 - 0.467score
analyze
miroo93
Run a read-only cross-artifact consistency check across spec.md, plan.md, and tasks.md for the current feature, before implementation.
SkillCFreshness: CClaude Code +9 - 0.467score
spec
miroo93
Create or update a feature spec.
SkillCFreshness: CClaude Code +9 - 0.467score
tasks
miroo93
Generate a tasks.md from plan.md for the current feature.
SkillCFreshness: CClaude Code +9 - 0.467score
tasks-to-issues
miroo93
Export the current feature's tasks.md into dependency-ordered GitHub issues for distributed/human tracking.
SkillCFreshness: CClaude Code +9 - 0.467score
implement
miroo93
Execute the tasks in tasks.md for the current feature.
SkillCFreshness: CClaude Code +9 - 0.467score
plan
miroo93
Generate a plan.md for the current feature from its spec.md.
SkillCFreshness: CClaude Code +9 - 0.467score
checklist
miroo93
Generate a requirements-quality checklist ("unit tests for the requirements") for the current feature on a chosen dimension like security, ux, or api.
SkillCFreshness: CClaude Code +9 - 0.446score
improve
miroo93
Use when the user wants to CHANGE, EXTEND, or UPDATE an existing feature that currently works as specified ("add X to Y", "also support Z", "change how Y does…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 10, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/miroo93/dev-workflows
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from miroo93
- 0.474score
pr
miroo93
Use when you have follow-up changes to get onto a pull request, when updating a PR after main moved on, when a PR has conflicts with its base, or when you are…
SkillCFreshness: CClaude Code +9 - 0.474score
projecthealth
miroo93
Use when the user asks "is the project healthy", "is CI green", "what's red", "are we deployable", "any failing checks", "is anything broken"…
SkillCFreshness: CClaude Code +9 - 0.471score
e2e-smoke
miroo93
Internal skill invoked by /feature, /improve, /troubleshoot to run a local real-browser smoke check against the running app and return PASS/FAIL/BLOCKED.
SkillCFreshness: CClaude Code +9 - 0.470score
troubleshoot
miroo93
Use when you (the human) found a bug while manually testing the app — an agent-built feature shows a wrong value, broken interaction, or console/runtime error…
SkillCFreshness: CClaude Code +9 - 0.467score
checklist
miroo93
Generate a requirements-quality checklist ("unit tests for the requirements") for the current feature on a chosen dimension like security, ux, or api.
SkillCFreshness: CClaude Code +9 - 0.467score
implement
miroo93
Execute the tasks in tasks.md for the current feature.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get projectstatus running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
projectstatus skill. Agent Mart. https://agentmart.dev/skills/miroo93-projectstatus (last updated 2026-10-24)