Tencent

Tencent/loli_profiler

Instructions file

Claude Code instructions for Tencent/loli_profiler, covering claude.md, project overview, build commands, prerequisites and build all.

Tencent/workbuddy-bench

Skill Claude CodeCodex

Use when generating analysis reports for WB-Bench-Office, WB-Bench-Web, or WB-Bench-Code from a single Harbor evaluation run artifact directory; route to the matching reference workflow.

Tencent/workbuddy-bench

Skill Claude CodeCodex

Use when a user wants to configure and launch a WorkBuddy Bench evaluation run from scratch, or is unsure how to set one up. Walks them interactively through environment setup, model config, .env credentials, job config, and launching the run, then hands off to wbbench-report-skills for metrics and trajectory analysis.

Tencent/WeChatReading

Skill Claude CodeCodex

A WeRead (微信读书) assistant for searching books, managing a bookshelf, viewing notes and highlights, browsing reviews, checking reading statistics, and finding recommendations.

Tencent/SkillHone

Instructions file CodexOpenCode

AGENTS.md instructions for Tencent/SkillHone, covering agent guide, pick the right skill, typical optimization flow, data boundaries and seed boundary.

Tencent/SkillHone

Skill Claude CodeCodex

Forgejo REST API toolkit — manage issues, pull requests, wikis, and repos on a Forgejo server. Use when the agent needs to file an issue, open / review / merge a PR, read or write a wiki page, or look up repo / branch info. One standalone script per resource type. Reads credentials from environment…

Tencent/SkillHone

Skill Claude CodeCodex

Run and interpret skill evaluations. Use when you need to evaluate a skill, run probe/test/PR-val, check if a PR regresses quality, compare two versions, or diagnose why the score dropped. Handles the full eval lifecycle including solver trajectory diagnosis for tool-level error detection.

Tencent/SkillHone

Agent

PR merge gate for skill-repo PRs. Runs the offline static check, produces a rubric score, posts the verdict as a Forgejo PR comment, and returns APPROVE or REQUESTCHANGES to the dispatching reviewer. Use only from skillhone-evaluation's reviewer flow, never from developer self-check.

Tencent/SkillHone

Agent

Analyze solver trajectories after a probe run to diagnose tool-level errors (rate limits, wrong tool names, script crashes) that proberesult.json doesn't capture. Dispatch after eval.py completes. Returns a redacted diagnosis JSON — safe to pass to the improver.

Tencent/SkillHone

Skill Claude CodeCodex

Optimize a skill by planning, exploring available tools, diagnosing failures, and implementing fixes via PR. Use this skill as soon as an optimization loop starts, especially on the first iteration when community tools or reference approaches should be explored before implementation.

Tencent/SkillHone

Agent

Pre-push self-check for a developer working on a skill. Runs the offline static check and produces a rubric score so the developer can decide whether to re-edit before pushing. Does NOT write PR comments or touch Forgejo.

Tencent/SkillHone

Agent

Picks up the latest open issue on the skill repo and implements a fix via branch → commit → PR workflow. One atomic change per PR.

Tencent/SkillHone

Agent

Discover new tools, APIs, and approaches that the skill doesn't know about yet. Searches community skill registries to find capabilities beyond what's currently implemented — browser automation, alternative search engines, specialized APIs, data extraction tools, etc. The goal is to expand the skill's toolbox, not…

Tencent/SkillHone

Agent

Analyzes probe evaluation results and creates a single focused Forgejo issue describing the highest-impact failure pattern to fix next.

Tencent/SkillHone

Agent

Reviews an open PR on the skill repo for quality, atomicity, and test-data leakage. Approves + merges if clean; otherwise requests specific changes.

Tencent/SkillHone

Skill Claude CodeCodex

Interactively gather a PRD (Product Requirements Document) for an agent skill that is about to be built or optimized by SkillHone. Use when the user says things like "I want to write a new skill", "help me spec this skill", "what should -skill do", or before running skillhone new / skillhone optim on a skill whose…

Tencent/SkillHone

Skill Claude CodeCodex

Use this skill to synthesize closed-form, automatically verifiable benchmark Q/A by exploring a tool environment, building a reusable exploration graph, and mining multiple hard questions from that graph. Use for: building a benchmark, writing eval items, generating evaluation data, closed-form QA, verifiable-answer…

Tencent/SkillHone

Agent

You explore the target environment and save a reusable graph. You do not write benchmark questions.

Tencent/SkillHone

Agent

You are the Deduper. You receive validated Q/A candidates from many seeds and produce the final benchmark set by removing structural duplicates and near-collisions. This is where "variety" stops being a per-seed concern and becomes a corpus-level concern.

Tencent/SkillHone

Agent

You turn Cartographer walks into closed-form Q/A candidates. You do not call tools and you do not invent missing facts.

Tencent/SkillHone

Agent

You decide whether each mined candidate is ready for the benchmark. Be skeptical: a clever-looking question can still be ambiguous, too easy, or ungradable.

Tencent/SkillHone

Skill Claude CodeCodex

SkillHone — toolkit for evaluating, optimizing, and managing agent skills. Use when asked to "evaluate a skill", "run probe", "optimize/iterate a skill", "create a new skill experiment", "seed a skill repo", or "run skill benchmarks"; also use when the user mentions a Forgejo-hosted skill repo and wants to measure or…

Tencent/workrally

Skill Claude CodeCodex

A command-line toolkit for producing AI-generated comic videos, from images and video to audio, prompts, projects, episodes, shots, storyboards, and media assets. CRUD means creating, viewing, editing, and deleting records.

Tencent/AgentlyMail

Skill Claude CodeCodex

An email-management tool operated from the command line, the text-based interface for running computer commands.