agentleFS
willcoliveirawillcoliveira/qualiow-exploratory-testing-skills/skills/qa-explore-report/SKILL.md

qa-explore-report

Skill15 starsChanged 17 days agoMITView on GitHub

Generate, regenerate, or reformat reports from existing exploratory testing sessions. Use when user says: "show report", "generate report", "reformat bugs", "session summary", or wants to review past session findings.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    bugs-only: all bugs sorted by severity, one line each with a link to bugs/BUG-NNN.md.

    line 74
  2. Very specific:

    All in output/sessions/<session-dir>/, confidentiality header first, redacted.

    line 86

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Exploratory Testing Report Generator

Reads any session kind (explore, quick, mobile, backend) written in the format of ${CLAUDE_SKILL_DIR}/../qa-explore/references/output-contract.md and produces a report in the same format. Session directories, index columns and the data-resolution order come from ${CLAUDE_SKILL_DIR}/../qa-explore/references/paths.md. Security: ${CLAUDE_SKILL_DIR}/../qa-explore/references/security-rules.md applies (redact before writing; confidentiality header first on every file). This skill runs in the qa-reporting-agent sub-agent (qualiow:qa-reporting-agent under a plugin install), in a forked context: it assembles what the session already wrote and never invents a finding, a severity or a verdict.

Input

  • session: session directory name or latest (default: latest)
  • format: markdown (default), summary, bugs-only, coverage-map
  • --overwrite: allow replacing an existing session-report.md

Flow

1. Find the Session

latest = the alphabetically last directory under output/sessions/ matching <YYYY-MM-DD-HHmm>-<kind>-<slug> (the scheme in paths.md; date-first means last = newest). List the directory names only; open no file outside the chosen session — not INDEX.md, not another session. A name given by the user must match exactly one directory; list the candidates if it is ambiguous.

2. Read Session Data

  • charter.md
  • session-log.md
  • progress.json, stats.json
  • phase-7-notes.md — the session's own summary, coverage rows, observations, recommendations and reflection; copy those sections, never invent them
  • phase-3-discovery.md, phase-4-journeys.md, phase-5-features.md, phase-6-edge-cases.md (explore and mobile sessions; quick sessions have none; backend sessions have ac-matrix.md, evidence/, expected-behaviour.md instead)
  • bugs/BUG-*.md
  • evidence-level.md, when it exists (a contract-2 session) — CLI-written; copied, never recomputed
  • the existing session-report.md, if any (its coverage map is the coverage source)

Size a file before you open it (wc -l <file>). A phase file or a report over 300 lines is read in windows: Grep '^## ' <file> for the headings, then Read with offset/limit on the sections you need. snapshots/ is raw page structure, not session evidence — never read it here.

3. Generate the Report

markdown (default): the full session report per output-contract.md (# Session Report — <target>, Session Metadata, Executive Summary, Summary Stats, Coverage Map with | Area | Risk | Status | Bugs | Notes |, Bugs Found, Observations, Areas Not Tested, Recommendations, Reflection, Session Stats; mobile and backend additions preserved; for a session with a verification/ directory, the Verification column in Bugs Found and ## Refuted Findings after Session Stats; for a session whose evidence-level.md exists, ## Coverage Level right after Executive Summary holding that file's body verbatim — all as qa-reporting-agent defines them). Never run qualiow session level from here: the level belongs to the session that computed it, and the command refuses a finalized session.

summary: copied, never composed — target, date and duration from stats.json; the bug count by severity from its severity_counts; ## Executive Summary and ## Recommendations verbatim from phase-7-notes.md (_Missing from phase-7-notes.md_ when absent); and the three highest-severity rows of ## Bugs Found, as the bug files spell them.

bugs-only: all bugs sorted by severity, one line each with a link to bugs/BUG-NNN.md.

coverage-map: a standalone coverage map from <data>/templates/coverage-map.md, filled from the session report's coverage table.

4. Write Output

  • markdown → session-report.md only if it does not exist or --overwrite was given; otherwise session-report.regenerated.md
  • summary → session-summary.md
  • bugs-only → bugs-summary.md
  • coverage-map → coverage-map.md

All in output/sessions/<session-dir>/, confidentiality header first, redacted. Never modify bugs/BUG-*.md from this skill. A reviewer's severity change lives in the session's feedback.md (/qa-explore-feedback), never in the bug files: the report keeps the severities the bugs carry.

Then check what you wrote:

qualiow session finalize output/sessions/<session-dir> --check

--check writes nothing; it validates stats.json, the confidentiality header on every artefact, the redaction list and the credential values, the verdict cross-check and contract 2, and on exit 1 prints a numbered list of violations naming each file. It does not read the report's layout — check that against the section list before you run it. Fix a missing header on a file you wrote and run it again; report anything you did not fix. Resolve the qualiow prefix per ${CLAUDE_SKILL_DIR}/../qa-explore/references/paths.md.

Present the result to the user.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.