What makes GitHub Release Analyzer notable?

991 downloads. Trust evidence available

How should GitHub Release Analyzer be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

GitHub Release Analyzer

Analyze GitHub repository releases and summarize release notes. Use when the user asks to analyze, summarize, review, or track the latest release or recent releases for a GitHub repo, including phrases like "分析最新 release", "latest release", "release 更新了什么", "汇总仓库 release", or requests to build a cron that tracks GitHub releases. Supports manual one-off analysis and cron-driven incremental tracking.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

991

Updated

Oct 11, 2026

Version

0.0.5

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 991 downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 991 downloadsadoption · observed Oct 11, 2026
Latest release: 0.0.5release · observed Aug 19, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 0.0.5release
Add Hermes compatibility, profile-scoped state storage, and platform compatibility tests.
Observed Aug 19, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s173r5y8tqy4nhexgndp34581984p37h:github-release-analyzer

Install using `clawhub skill install s173r5y8tqy4nhexgndp34581984p37h:github-release-analyzer` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/stoner-byte/github-release-analyzer before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-stoner-byte-github-release-analyzer/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

61,904 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: github-release-analyzer
version: 0.0.5
description: Analyze GitHub repository releases and summarize release notes. Use when the user asks to analyze, summarize, review, or track the latest release or recent releases for a GitHub repo, including phrases like "分析最新 release", "latest release", "release 更新了什么", "汇总仓库 release", or requests to build a cron that tracks GitHub releases. Supports manual one-off analysis and cron-driven incremental tracking.
metadata:
  openclaw:
    emoji: "📦"
    requires:
      bins: [python3]
  hermes:
    tags: [github, releases, monitoring, cron]
---

# GitHub Release Analyzer

Use this skill as a fixed pipeline:

```text
prepare -> summarize -> render -> deliver -> commit
```

Only `summarize` is free-form. `prepare`, `render`, and `commit` are deterministic script steps.

## Inputs

- Repo input: `https://github.com/<owner>/<repo>` or `<owner>/<repo>`
- Default `stateKey`: `{owner}__{repo}`
- Default template: `default`
- Default behavior:
  - manual: latest formal release only, no state read/write
  - cron: formal releases only, first run selects latest only, later runs select unprocessed only

## Workflow

Before running any `scripts/...` command, set the command working directory to
the directory containing the loaded `SKILL.md` (the Skill root). Do not run
these commands from the OpenClaw workspace root. This does **not** require a
shell `SKILL_DIR` environment variable: OpenClaw uses the loaded Skill's
installed directory, and Hermes uses the `skill_dir` returned by `skill_view`.

1. Read `references/execution-modes.md` and choose `manual` or `cron`.
2. From the Skill root, run:

```bash
python3 scripts/run.py prepare --repo <repo> --mode <manual|cron>
```

Useful flags:

- `--state-key <key>`
- `--limit <n>`
- `--include-prerelease`
- `--output-template default`
- `--initial-cron-behavior latest-only`

3. If `status=has_updates`, read `references/summary-contract.md` and produce one summary string per selected release.
   Keep the summary language aligned with the primary language of the invocation instruction.

4. Render the final message:

```bash
python3 scripts/run.py render --repo <repo> --mode <manual|cron> < payload.json
```

When building the `render` payload, preserve the release fields required by `render`, especially `tag_name`, `published_at`, and `html_url`.

5. In cron mode, after successful delivery, commit state:

```bash
python3 scripts/run.py commit \
  --repo <repo> \
  --mode cron \
  --processed-tags <comma-separated-tags> \
  --latest-release-id <id> \
  --latest-published-at <iso8601>
```

## Rules

- Treat `prepare` output as the source of truth for selection, ordering, first-run behavior, repo normalization, and state path.
- The output language must follow the primary language of the invocation instruction.
- The final outgoing message must come from `render`.
- In cron mode:
  - if `status=no_update` or `status=no_release`, reply with `NO_REPLY`
  - if `status=has_update

README.md

# github-release-analyzer

Current planned release version: **0.0.1**

Analyze GitHub releases and turn release notes into short, high-signal summaries.

## What it does

- Supports a single repo input: `owner/repo` or `https://github.com/owner/repo`
- Manual mode: summarize the latest formal release
- Cron mode: track unprocessed formal releases incrementally
- Preserves a deterministic pipeline:
  `prepare -> summarize -> render -> commit`

## Main files

- `SKILL.md` — skill routing + workflow rules
- `scripts/run.py` — deterministic entrypoint for `prepare`, `render`, `commit`
- `references/execution-modes.md` — manual vs cron behavior
- `references/summary-contract.md` — required summary output shape

## Notes

- Requires `python3`
- Default state is stored under `~/.openclaw/workspace/state/github-release-analyzer/`
- Cron mode returns `NO_REPLY` when there is no new formal release to report

## Initial publish target

- License: MIT
- Initial version: `0.0.1`

_meta.json

{
  "ownerId": "kn7bapcyjfbh5hs3fty4kvxann84pre4",
  "slug": "github-release-analyzer",
  "version": "0.0.5",
  "publishedAt": 1787114293411
}

references/execution-modes.md

# Execution Modes

## Manual

Required path:

1. `prepare --mode manual`
2. If `status=no_release`, reply that no formal release exists
3. If `status=has_updates`, summarize exactly the selected `releases[]`
4. Build `summaries[]`
5. `render --mode manual`
6. Reply with the rendered `message`

Do not:

- read or write state
- call `commit`
- analyze more than the selected latest formal release
- add workflow narration or extra preambles

## Cron

Required path:

1. `prepare --mode cron`
2. If `status=no_release` or `status=no_update`, reply exactly `NO_REPLY`
3. If `status=has_updates`, summarize exactly the selected `releases[]`
4. Keep `prepare` ordering
5. Build `summaries[]`
6. `render --mode cron`
7. Deliver the rendered `message`
8. After successful delivery, `commit`

Do not:

- skip `prepare`
- bypass `render`
- write processed state before delivery succeeds
- when `status=no_update` or `status=no_release`, reply exactly `NO_REPLY`
- emit progress narration, step labels, intermediate JSON, or any workflow text to the delivery target

## Cron prompt shape

Keep cron instructions short and mechanical. The useful constraints are:

- use this skill in cron mode
- run deterministic `prepare` first
- summarize only formal releases selected by `prepare`
- first run: latest only
- later runs: unprocessed only, ordered old to new
- no update: reply exactly `NO_REPLY`
- only emit the final rendered message
- after successful delivery, commit state

references/state-format.md

# State Format

Default paths:

```text
Hermes: $HERMES_HOME/state/github-release-analyzer/{stateKey}.json
OpenClaw legacy (when populated): ~/.openclaw/workspace/state/github-release-analyzer/{stateKey}.json
OpenClaw persistent: ~/.openclaw/state/github-release-analyzer/{stateKey}.json
```

`GITHUB_RELEASE_ANALYZER_STATE_ROOT` overrides the default root on either
platform. When `HERMES_HOME` is set, the Hermes path is used. Otherwise,
OpenClaw preserves its existing legacy-then-persistent fallback behavior.

Schema:

```json
{
  "repo": "openclaw/openclaw",
  "processed_tags": [],
  "latest_processed_release_id": null,
  "latest_processed_published_at": null,
  "last_checked_at": null,
  "last_success_at": null,
  "initialized_at": null
}
```

Rules:

- derive `stateKey` from normalized repo unless explicitly overridden
- missing file or empty `initialized_at` means first run
- first cron run summarizes the latest formal release only
- `prepare` updates `last_checked_at`
- `commit` updates processed tags and latest processed metadata only after successful delivery
- failed fetch, summarize, render, or delivery must not mark releases as processed

Github ReposUpdated 3d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular