Generate Report

Synthesize experiment results into a structured research report in the research/ folder. Supports --inconclusive flag.

5 stars 1 forksResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add TalonT-Org/AutoSkillit --skill generate-report
Manual install
git clone --depth 1 https://github.com/TalonT-Org/AutoSkillit.git /tmp/AutoSkillit
mkdir -p ~/.claude/skills
cp -r /tmp/AutoSkillit/src/autoskillit/skills_extended/generate-report ~/.claude/skills/generate-report

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Write Report Skill

Synthesize scope findings, experiment design, and experiment results into a
structured research report. The report is committed to the `research/` directory
in the worktree and becomes the primary deliverable of the research recipe.

This skill handles both conclusive and inconclusive outcomes — inconclusive
results are valid findings, not failures.

## When to Use

- As the reporting step of the `research` recipe (phase 2)
- After `/autoskillit:run-experiment` has produced results (or after retry exhaustion)

## Arguments

```
/autoskillit:generate-report {worktree_path} {results_path} [--inconclusive]
[--output-mode {local|pr}] [--issue-url {url}]
[--experiment-type {type}] [--methodology-traditions {tradition}]
```

- `{worktree_path}` — Absolute path to the worktree (required). First path-like
  token after the skill name.
- `{results_path}` — Absolute path to the experiment results file (required).
  Second path-like token.
- `--inconclusive` — Optional flag indicating experiments were inconclusive
  (retry exhaustion or insufficient evidence). When present, the report
  emphasizes what was learned and why evidence was insufficient, rather than
  framing as a failure.
- `--output-mode {local|pr}` — Optional. When 'local', the report header must include an
  issue reference link if `--issue-url` is also provided.
- `--issue-url {url}` — Optional. GitHub issue URL. When output_mode=local and this is
Read the full skill on GitHub

Details

Skill name
generate-report
Path
src/autoskillit/skills_extended/generate-report/SKILL.md
License
MIT
Repo updated
8 November 2026

FAQ

What does the Generate Report skill do?

Synthesize experiment results into a structured research report in the research/ folder. Supports --inconclusive flag.

How do I install the Generate Report skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add TalonT-Org/AutoSkillit --skill generate-report. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Generate Report popular?

It lives in TalonT-Org/AutoSkillit, which has 5 GitHub stars and 1 forks.

Related skills

Analyze Prs

5

TalonT-Org/AutoSkillit

Analyze all open PRs targeting a base branch — determine merge order, identify file overlaps, and tag each PR as simple or needs_check for complexity. Use at the start of a PR consolidation workflow.

Git & Code Review

Arch Lens C4 Container

5

TalonT-Org/AutoSkillit

Create C4 Container architecture diagram showing static structure, building blocks, and technology choices. Anatomical lens answering "How is it built?

Software Development

Arch Lens Concurrency

5

TalonT-Org/AutoSkillit

Create Concurrency architecture diagram showing parallel execution patterns, thread pools, synchronization, and barriers. Physiological lens answering "How does parallelism work?

Software Development

Resolve Claims Review

5

TalonT-Org/AutoSkillit

Fetch claim findings from audit-claims, run citation-aware intent validation (ACCEPT/REJECT/DISCUSS), apply targeted citation fixes, escalate findings requiring experiment reruns, and post inline replies.

Research & Science

Audit Claims

5

TalonT-Org/AutoSkillit

Parallel subagent-driven claim extraction and citation integrity audit for research PRs. Extracts claims by section, matches against available evidence, classifies unsupported claims as findings, and emits a verdict for recipe routing.

Research & Science

Resolve Research Review

5

TalonT-Org/AutoSkillit

Fetch PR review comments from review-research-pr, run research-aware intent validation (ACCEPT/REJECT/DISCUSS), apply targeted fixes, escalate unrerunnable findings, and post inline replies. Exit 0 drives recipe re_push_research; exit non-zero halts the cycle.

Research & Science

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.