How do I install the Progress skill?

Run npx skillmds@latest add sashamarchuk/progress-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Progress safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Progress?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Progress free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Progress?

SashaMarchuk (@sashamarchuk) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Progress by sashamarchuk — Agent Skill

Name: Progress
Author: SashaMarchuk

File contents

Role

Read-only. Display state.json nicely. No mutations.

Invocation

/ultra-analyzer:progress [run-name]

If run-name omitted: auto-detect single run or list available.

Protocol

Step 1: Locate run

Same rules as /ultra-analyzer:run Step 1.

Step 2: Read state

cat <RUN_PATH>/state.json | jq .

Step 3: Format output

analyzer run: <run-name>
  created: <created_at>   updated: <updated_at>
  source:  <connector_hint>
  status:  <status>       step: <current_step>

Ultra gates:
  pre-discover:   <verdict>  [<report-path-if-any>]
  pre-synthesize: <verdict>  [<report-path-if-any>]

Counters:
  topics   total=<N>  done=<D>  failed=<F>  pending=<P>  in-progress=<IP>
  findings passed=<FP> failed=<FF>

Last checkpoint: <path>

Next action:
  <step-specific guidance — see below>

Next-action guidance by current_step

current_step	status	next action
init	pending	Edit config.yaml + seeds.md, then /ultra-analyzer:run
pre-discover-gate	pending	/ultra-analyzer:run (will invoke /ultra Gate 1)
pre-discover-gate	blocked	Edit config/seeds per remediation in validation/gate1-*.md, then /ultra-analyzer:run
discover	running	Wait for discover to complete, then /ultra-analyzer:run
analyze	running	Open terminals: bash ${CLAUDE_PLUGIN_ROOT}/bin/launch-terminal.sh
analyze	blocked	Low PASS rate. Inspect validation/findings/*.json for patterns. Fix worker or seeds.
pre-synthesize-gate	pending	/ultra-analyzer:run (will invoke /ultra Gate 2)
pre-synthesize-gate	blocked	Revise flagged topics per validation/gate2-*.md, re-run workers, then /ultra-analyzer:run
synthesize	running	Wait for REPORT.md generation
done	passed	Read synthesis/REPORT.md
failed	failed	Inspect run.log

Step 4: Optional detail flags

If $ARGUMENTS contains --verbose, also print:
- last 20 lines of run.log
- list of failed topics (names only)
- list of findings with FAIL verdict (names + reason)

Hard rules

Never mutate state. Read-only.
Always show the "next action" line — user should never have to guess what to do.

---name: progress-2description: Show current analyzer run status in a human-readable format. Reads state.json and prints the pipeline step, counters, gate verdicts, and what the user should do next.---# RoleRead-only. Display state.json nicely. No mutations.# Invocation /ultra-analyzer:progress [run-name]If run-name omitted: auto-detect single run or list available.# Protocol## Step 1: Locate runSame rules as /ultra-analyzer:run Step 1.## Step 2: Read state```bashcat <RUN_PATH>/state.json | jq .```## Step 3: Format output```analyzer run: <run-name> created: <created_at> updated: <updated_at> source: <connector_hint> status: <status> step: <current_step>Ultra gates: pre-discover: <verdict> [<report-path-if-any>] pre-synthesize: <verdict> [<report-path-if-any>]Counters: topics total=<N> done=<D> failed=<F> pending=<P> in-progress=<IP> findings passed=<FP> failed=<FF>Last checkpoint: <path>Next action: <step-specific guidance — see below>```## Next-action guidance by current_step| current_step | status | next action ||---|---|---|| init | pending | Edit config.yaml + seeds.md, then /ultra-analyzer:run || pre-discover-gate | pending | /ultra-analyzer:run (will invoke /ultra Gate 1) || pre-discover-gate | blocked | Edit config/seeds per remediation in validation/gate1-*.md, then /ultra-analyzer:run || discover | running | Wait for discover to complete, then /ultra-analyzer:run || analyze | running | Open terminals: bash ${CLAUDE_PLUGIN_ROOT}/bin/launch-terminal.sh <RUN_PATH> || analyze | blocked | Low PASS rate. Inspect validation/findings/*.json for patterns. Fix worker or seeds. || pre-synthesize-gate | pending | /ultra-analyzer:run (will invoke /ultra Gate 2) || pre-synthesize-gate | blocked | Revise flagged topics per validation/gate2-*.md, re-run workers, then /ultra-analyzer:run || synthesize | running | Wait for REPORT.md generation || done | passed | Read synthesis/REPORT.md || failed | failed | Inspect run.log |## Step 4: Optional detail flags- If `$ARGUMENTS` contains `--verbose`, also print: - last 20 lines of run.log - list of failed topics (names only) - list of findings with FAIL verdict (names + reason)# Hard rules- Never mutate state. Read-only.- Always show the "next action" line — user should never have to guess what to do.

Frequently asked questions

Progress