OpenBiliClaw: Skill for Claude Code

.claude/skills/writing-specs/SKILL.md

writing-specs is a skill for Claude Code from whiteguo233/OpenBiliClaw. It costs 20 tokens per session (1,072 once invoked), scanned A, original, MIT.

A documentation-first workflow for writing a software design specification and an implementation plan before changing code.

In plain words
What is it for?
Use it when planning a feature or several related tasks to create matching dated spec and plan files, document the current problem and design rules, and define how the result will be verified.
Why use it?
It makes the intended behavior, evidence, limits, and verification steps explicit before implementation begins, while requiring the documents to be committed separately first.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is whiteguo233/OpenBiliClaw's own configuration. It tells Claude Code how to work on OpenBiliClaw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything OpenBiliClaw configures →

About the project

OpenBiliClaw is a local, open-source AI agent that learns a person's interests and discovers content across multiple social platforms and the open web. It is for people who want personalized content recommendations with their usage data kept on their own machine.

whiteguo233/OpenBiliClaw · 3,278 stars · on GitHub · whiteguo233.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to whiteguo233/OpenBiliClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/whiteguo233/OpenBiliClaw/main/.claude/skills/writing-specs/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/whiteguo233/OpenBiliClaw

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for writing-specs

README.md
[![agentmods](https://agentmods.dev/badge/skills/whiteguo233/openbiliclaw/writing-specs/github.svg)](https://agentmods.dev/skills/whiteguo233/openbiliclaw/writing-specs)
Your own site
<a href="https://agentmods.dev/skills/whiteguo233/openbiliclaw/writing-specs"><img src="https://agentmods.dev/badge/skills/whiteguo233/openbiliclaw/writing-specs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for writing-specs

Your own site · 80×15
<a href="https://agentmods.dev/skills/whiteguo233/openbiliclaw/writing-specs"><img src="https://agentmods.dev/badge/skills/whiteguo233/openbiliclaw/writing-specs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,072 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 108
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.01072
Opus 5 $0.00010 $0.00536
Sonnet 5 $0.00004 $0.00214
Haiku 4.5 $0.00002 $0.00107

Measured 11d ago against content hash 921856c728a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

writing-specs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/writing-specs/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Specs and Plans

Produce an authoritative design spec and an executable implementation plan before changing code. Resolve every placeholder against the live repository.

Name and commit the pair first

Create both documents with the same dated slug:

  • docs/plans/YYYY-MM-DD-<slug>-spec.md
  • docs/plans/YYYY-MM-DD-<slug>-plan.md

Commit the pair as docs: add <feature> spec and plan before implementation. Do not mix code into this docs-first commit.

SPEC skeleton

# <Feature> Spec — <measurable outcome>

**Created:** YYYY-MM-DD
**Scope:** <affected behavior, modules, and integrations>
**Out of scope:** <explicit non-goals>

## Goal

State the current cost or failure, quantified target outcomes, and the exact commands that
verify them.

## Design invariants (MUST hold in every phase)

1. **<Invariant name>:** <falsifiable rule and verification surface>.
2. **<Invariant name>:** <falsifiable rule and verification surface>.

## Current diagnosis

### D1. <Observed problem>

Record evidence at `path/to/file.py:line`; distinguish confirmed facts from hypotheses.

### D2. <Observed problem>

Record the caller, data flow, failure mode, and existing test coverage with `file:line` evidence.

## Priority classification

| Phase | Content | Tier | Why |
| --- | --- | --- | --- |
| 0 | <gate or prerequisite> | **MUST** | <risk it controls> |
| 1 | <main change> | RECOMMENDED | <measured leverage> |

List dependencies, then group work into **Wave A**, **Wave B**, and later waves by risk and
dependency. State what can ship independently and where work may safely stop.

## Phase designs

### Phase 0 — <name>

Define interfaces, algorithms, error behavior, tests, rollout, and numeric acceptance gates.

## Expected impact

| Lever | Measured effect |
| --- | --- |
| <phase> | <quantified result> |

## Documentation obligations

List every module doc, changelog, architecture diagram, CLI/config reference, installer doc,
and README surface triggered by the design.

Read the full file on GitHub · 140 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 140 lines · 20 tokens per session scan A 921856c728a2

Subscribe to this mod's changes

writing-specs is a skill published in the GitHub repository whiteguo233/OpenBiliClaw (3,278 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 1,072 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories