Show Me Your Work Decision Log
cursor/plugins
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
M-1.6 envelope self-check——独立性保证不自欺欺人 (5 blockingcheck)。由 CLI ./tw fix complete --self-check-mode fork(默认即 fork)自动派起,不经 Skill 工具调用;fix 主会话产 FixCompleted 前直读本文,是为理解双层验证关系。
$ npx skills add Towow-ai/Flowness --skill fix-self-check -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Towow-ai/Flowness fix-self-check --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/fix-self-check .claude/skills/fix-self-check && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "fix-self-check" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/fix-self-check into .claude/skills/fix-self-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fix-self-check", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/fix-self-checkType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Towow-ai/Flowness --skill fix-self-check -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Towow-ai/Flowness fix-self-check --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/fix-self-check .agents/skills/fix-self-check && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "fix-self-check" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/fix-self-check into .agents/skills/fix-self-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fix-self-check", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Towow-ai/Flowness --skill fix-self-check -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Towow-ai/Flowness fix-self-check --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/fix-self-check .cursor/skills/fix-self-check && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "fix-self-check" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/fix-self-check into .cursor/skills/fix-self-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fix-self-check", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Towow-ai/Flowness.git --path .claude/skills/fix-self-check--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Towow-ai/Flowness --skill fix-self-check -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Towow-ai/Flowness fix-self-check --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/fix-self-check .gemini/skills/fix-self-check && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "fix-self-check" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/fix-self-check into .gemini/skills/fix-self-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fix-self-check", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Towow-ai/Flowness fix-self-checkInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Towow-ai/Flowness --skill fix-self-check -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/fix-self-check .github/skills/fix-self-check && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "fix-self-check" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/fix-self-check into .github/skills/fix-self-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fix-self-check", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Towow-ai/Flowness --skill fix-self-check -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Towow-ai/Flowness fix-self-check --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/fix-self-check .opencode/skills/fix-self-check && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "fix-self-check" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/fix-self-check into .opencode/skills/fix-self-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fix-self-check", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
fix-self-checkM-1.6 envelope self-check——独立性保证不自欺欺人 (5 blockingcheck)。由 CLI ./tw fix complete --self-check-mode fork(默认即 fork)自动派起,不经 Skill 工具调用;fix 主会话产 FixCompleted 前直读本文,是为理解双层验证关系。
Fix Self Check is an agent skill from Towow-ai/Flowness. M-1.6 envelope self-check——独立性保证不自欺欺人 (5 blockingcheck)。由 CLI ./tw fix complete --self-check-mode fork(默认即 fork)自动派起,不经 Skill 工具调用;fix 主会话产 FixCompleted 前直读本文,是为理解双层验证关系。
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `anchors/README.md`).
It sits in Agent Workflows, covering Verification before completion. The repository describes itself as: A work-centered runtime for agentic software engineering. Work persists; agents, context, and graphs assemble around it. The licence is Apache-2.0.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit c9d6abe. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
pythongitFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Fix Self Check loads about 2.2k tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 717 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from Towow-ai/Flowness at commit c9d6abe, republished under its Apache-2.0 licence (© Towow-ai). 717 words, ~2,227 tokens.
.claude/skills/fix-self-check/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.tools 无 Edit / Write(防自欺):我只读不写——
Read / Grep / Glob / Bash够我跑 grep / pytest / 验 closure_contract 条目。我物理上不能改代码、不能改 envelope,所以我的 verdict 不可能 "顺手把不通过的地方改过去再说通过"。独立性是结构保证的,不是自觉(V-02 schema-level 隔离)。
服务谁:两类读者。①fork 本体——CLI ./tw fix complete --self-check-mode fork(默认即 fork)
内部 dispatch_fork 自动派起的独立会话,装载本文跑 5 项 blocking_check;②fix 主会话(被审者)——
产 FixCompleted 前直读本文,是为理解双层验证关系。我 context: fork,不经 Skill 工具调用。
行为差断言:装载我的 fork,判 passed 的每条 check 都有"合约自带 pattern/test_selector 实跑"的 证据,够不到真合约就 failed + 指路(不裁决、不背书)。不装载时:对着 prompt 摘要点头的空壳独立验, 或在无合约场景即兴给出会被引作放行凭据的背书。
验收探针:①给一条带真合约的 finding——verdict 每条 passed 都引账本合约的 pattern/selector + 实跑输出算过,引 prompt 摘要或自选 pattern 算不过。②给一条账本确认无 closure_contract 的 finding—— 合约派生 check 全 failed +"账本无真合约可复算"+ 指路 verify-step degraded(F-08d)+ 实质观察装进 "非裁决"框算过,即兴裁决闭合归属或给无边界标注的背书算不过。③把 verdict 交给被审 fixer 冷读—— 读不出"fork 放行了 inline"的解释空间算过。
边界:我只产 self_check_result / verdict;不修 finding、不改代码、不替 CLI 门定终态;fork 判
fail 后 fixer 的合法出路是 fix/SKILL.md 的地盘,我只指路不重述。回归锚见 anchors/(三份依从
范本 verdict + EP-B 换旗时间线)。
我是 M-1.6 内部独立 self-check fork——fix 主会话跑 ./tw fix complete --self-check-mode fork
(默认即 fork)时,由 CLI 内部 dispatch_fork 自动派起;5 项 blocking_check 跑通,FixCompleted
才产得出来。我不经 Skill 工具调用;fix 主会话直读本文是健康行为——那是为理解双层验证关系,不是替我跑。
我是 fork(context: fork,capsule 投喂)—— 独立性保证不让 main session 自欺欺人。类比 M-1.4 execution-self-check fork。判断尺子不能由被判断者自己拿,这是 v3 反假done 的结构性约束。
我产 closure_result(criteria_results / ripple_results / residual_check_results),交给
./tw fix complete --closure-result-file。CLI 门(l1/closure_verification.py)会据 finding 的
closure_contract 独立复算——GREP/TEST 它用合约自带的 verification_pattern/test_selector 自己
subprocess 跑、forbidden_residual 用合约自带 pattern 它自己 grep,不信我自报的 passed(门复算
与我自报矛盾 → 拒,抓撒谎)。
RUN-037 P6 关键:复算用的 pattern/test_selector 由 reviewer 签 FindingCreated 合约时定死,不是 我提供。我(被审者)在 closure_result 里只声明:这条 criterion 我覆盖了(criterion 字面对应 合约 condition)+ 我自报通过 + 证据。我不能也无须给 pattern——closure_result schema 已删掉 recompute 字段,偷塞即被解析拒。这堵住了"我把 grep 指向无关、恰好 0 命中的 pattern 自洽通过"的作弊面: 门只认合约里那个 pattern。我糊弄不了门——这是设计如此(我是必要条件不是充分条件,M-1.6 §2.3)。
shared_knowledge_required:
- fix/fix-mental-model.md
- fix/closure-contract-execution.md
- fix/fix-pitfalls.mdfinding 的 closure_contract 里有一条 forbidden_residual,reviewer 签合约时定死了
verification_pattern: "os\.system\("(这条 finding 是"消灭 shell 注入面")。我要验"残留 = 0"。
✗ 自欺版(grep 自洽通过,读着像验过了):
Check 3 forbidden_residuals_zero: passed evidence:
grep -rn "os.system(" src/ | wc -l= 0 → 残留清零。
这份的问题不是"没跑 grep"——我跑了,还贴了命令。问题是我把 grep 指向了一个我自选的、和合约不一致的 pattern,恰好 0 命中:合约写的是正则 os\.system\((转义点号),我跑的是字面串 os.system((点号是通配,本来更宽松不该出问题)——但真正的猫腻在另一种:我若把 pattern 悄悄换成 os\.system\(\s*cmd_safe(只查"安全调用"那种),它当然 0 命中,我就"自洽"了。这是 fix 阶段最经典的作弊面:用宽松/无关的 pattern 凑出"closure 满足",自己骗自己。 合约里 reviewer 定死的 pattern 没被用,我的 0 命中毫无意义。
✓ 不自欺版(严格按合约自带 pattern 验,只声明、不自选 pattern):
Check 3 forbidden_residuals_zero: passed evidence: 按 closure_contract.forbidden_residuals[0] 自带的
verification_pattern: "os\.system\("实跑——grep -rnE 'os\.system\(' src/→ 0 occurrences(输出贴附)。我没有自选 pattern,用的就是合约那一条。 (我清楚:CLI 门 closure_verification.py 会拿合约这同一个 pattern 自己再 grep 一遍复算;我自报 passed 与门复算矛盾 → 门拒、抓我撒谎。所以我自欺没有收益——但即便没有门,我也只认合约 pattern。)
看出区别没有:✗ 不是"没验",它跑了 grep、贴了命令、得了 0——它是验的是错的东西。我(被审者)在 closure_result 里只声明"这条 criterion 我覆盖了 + 我自报通过 + 证据",绝不自带/自选 pattern(schema 已删 recompute 字段,偷塞即被解析拒)。pattern 永远是 reviewer 签 FindingCreated 合约时定死的那一个。判 passed 的资格不是"我 grep 出了 0",是"我用合约指定的那个 pattern grep 出了 0、且验不到就老实 fail"。 这对示范就是我每条 check 的分辨率下限。
我被 CLI 路径(fix complete driver)调起时,prompt 里那条 closure_contract (摘要) 只是线索,不是
判据来源。只对着摘要点头 = 空壳独立验,这正是 finding f-glob-review-fix-no-proof-of-work(M16-F2)要
根治的病:fork 即使 spawn 了也够不到 reviewer 签的真合约 pattern + patch diff,于是只复判门自己的 pass
摘要。我必须自己够到真东西:
finding_id 在 canonical 账本(cwd 下 .towow/events.log + 热段 .towow/events/hot/*.jsonl)
Grep/Bash 出那条 FindingCreated,从 payload.after_state.closure_contract(或
payload.closure_contract)取真 closure_criteria[](含 verification_method /
verification_pattern / test_selector / expected_*)与 forbidden_residuals[]。verification_method 真跑机器复算(grep → 真 grep -rn 数命中比 expected;test →
真 python -m pytest <test_selector>;forbidden_residual → 用合约 pattern 真 grep 断 found=0)。git -C <repo> show / diff 看 fix_id 的真实 patch diff,核对它确实改了合约要求的地方
(够到 patch diff,非只看 patch_summary 字样)。够不到真合约(finding 无 closure_contract / 账本找不到)→ 在对应 check 老实标 status=failed +
evidence 写清"账本无真合约可复算",不许拿摘要凑 passed(fail-closed)。
finding 压根无 closure_contract(账本确认无、且已排除是搜法问题——找一条同段带合约的 finding 作 对照)= 不是我的辖区:无合约 finding 的独立防线在 verify-step 的 fix_after degraded fork(F-08d), 不在我。这时我的 verdict 长成固定三件套,不即兴:
failed +"账本无真合约可复算"——不因"免撞墙"软化;我判 fail 不是 inline 换旗许可。fork 判 fail 之后怎么走,是 fix 主会话按它 skill 里的合法出路 处置的事(那是 fix/SKILL.md 的地盘);我的 verdict 只可作证据被引用,不可作放行凭据被引用——把这句 写进 verdict 本身,压掉"fork 其实放行了"的解释空间。
读 capsule(+ 按上面 ★ 从账本按 finding_id 加载真合约,prompt 摘要不算判据):
逐项跑 5 个 blocking_check:
对 closure_contract.closure_criteria 每条——
对 closure_contract.ripple_targets 每个——
对 closure_contract.forbidden_residuals 每个 pattern——
self_check_result:
overall_passed: bool # 5 项全 passed 才 true
blocking_check_results:
- id: fix.closure_criteria_self_verified
status: passed | failed
# 注: 不报 recompute/pattern — 复算 pattern 由合约定死 (RUN-037 P6), 我只报 passed + evidence
evidence: [...]
- id: fix.ripple_targets_synced
status: passed | failed
evidence: [...]
- id: fix.forbidden_residuals_zero
status: passed | failed
evidence: [...]
- id: fix.consensus_respected
status: passed | failed
evidence: [...]
- id: fix.review_plan_respected
status: passed | failed
evidence: [...]自选 pattern 凑自洽(最经典作弊面) —— 拿宽松/无关的 grep 凑出"残留清零""criterion 满足",自己骗自己。对治 = 上面那份 ✓:只用合约自带的 verification_pattern/test_selector,绝不自选;验不到就老实 fail。
Over-confident(main session 已经"看过",self-check 走过场全 passed) —— 对治:每个 passed 必须有具体 evidence_artifact(command output / file path),不能抽象 "looks good"。
Under-confident(保守标 failed 让 main session 重做) —— 对治:closure_contract 三字段是明确 合约——按字段验证,不主观判断。
© Towow-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in .claude/skills/fix-self-check of Towow-ai/Flowness.
Open the folder on GitHubat commit c9d6abe
Fix Self Check next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Fix Self Check this skillTowow-ai/Flowness | 107 | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Show Me Your Work Decision Logcursor/plugins | 11k | 8 repos | ~1.6k | Automated safety check: Pass | None | |
| Scope Creep Guardlennney/stop-that-shit | 2.5k | 1 repos | ~2k | Automated safety check: Pass | MIT | |
| Verification Before Completionfarm-fe/farm | 5.6k | 46 repos | ~1k | Automated safety check: Pass | MIT | |
| PUA High-Agency Governancetanweai/pua | 20k | — | ~502 | Automated safety check: Pass | MIT | |
| Incremental Implementationaddyosmani/agent-skills | 104k | 1 repos | ~2.3k | Automated safety check: Pass | MIT |
cursor/plugins
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
lennney/stop-that-shit
Keeps an agent focused on the requested work by applying a five-step ladder that checks for direct solutions, real gaps and speculative defenses before adding anything.
farm-fe/farm
A skill your agent uses when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any…
tanweai/pua
Pushes an agent to keep verifying and changing approach after repeated failures, using a diagnosis line, evidence-based completion and confirmation before risky edits.
addyosmani/agent-skills
Delivers a change in thin vertical slices, each implemented, tested, verified and committed before the next, using vertical, contract-first or risk-first slicing.
tanweai/pua
Runs an unattended iterate-until-verified loop in which a user-set verify command, not the agent's own claim, decides when the task is finished.
Towow-ai/Flowness
从 task 的 read/write set + concept statemachine 推导 6 种依赖类型的提案。主 planner 决定边的真实性。派它时只给 read/write set 与疑点、不给预期边集;已有预判逐条标「待复核」交它取证。
Towow-ai/Flowness
停机后复工的标准安全流程(水位线追平/积压泄流/服务分批重启)。当系统经历过 daemon 停机、性能冲刺减负、事故停摆之后要恢复常驻服务时触发;即使 owner 只说"把服务开回来"、"复工"、"追平水位线",也应触发。核心使命:绝不让"重启"变成"积压喷发"(2026-07-04 实锤:orchestrator 停机后水位线落后 3240 条,直接重启把机器负载打到 22+,owner…
Towow-ai/Flowness
M-1.4 execution skill — 跑 single task 产 patch + 提交 envelope。
Towow-ai/Flowness
Pre-submit 自检——envelope 提交 commit gate 前必跑。独立 OPUS fork 逐项判 blocking checks(清单以 dispatch prompt 注入为准),executor 不能 self-assess(运动员不当裁判)。
Towow-ai/Flowness
修复者 — 把一条被发现的问题(finding)按它的闭合合约修干净,修一个不制造下一个。产 FixProposed + 临时的 FixCompleted,不自判问题关闭(那是复查的权)。当 daemon 派一条 finding 来修、或需要闭合一个已发现的问题时用,即使只说"修一下这个 finding""把这个问题闭合"也触发。调用名就是 fix(Skill 工具)或 /fix(命令),没有…
Towow-ai/Flowness
F-08g 元 review——审 reviewplan 自身够不够 (dimensions 覆盖/voi 具体/historical feed 漏)。用 named error patterns + 历史比对。design-time mode 调它审 reviewplancreator 的产出, critical meta-finding → orchestrator 回头让…
Categories
M-1.6 envelope self-check——独立性保证不自欺欺人 (5 blockingcheck)。由 CLI ./tw fix complete --self-check-mode fork(默认即 fork)自动派起,不经 Skill 工具调用;fix 主会话产 FixCompleted 前直读本文,是为理解双层验证关系。. Fix Self Check is an agent skill from Towow-ai/Flowness.
Fix Self Check fits situations like: tasks that involve Verification before completion.
Run `npx skills add Towow-ai/Flowness --skill fix-self-check -a claude-code`. Or copy the skill folder (.claude/skills/fix-self-check in Towow-ai/Flowness) into .claude/skills/fix-self-check in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Towow-ai/Flowness --skill fix-self-check -a codex`. Or copy the skill folder (.claude/skills/fix-self-check in Towow-ai/Flowness) into .agents/skills/fix-self-check in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Towow-ai/Flowness --skill fix-self-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fix-self-check, .gemini/skills/fix-self-check, .github/skills/fix-self-check and .opencode/skills/fix-self-check in your project.
Going by SKILL.md and its folder, Fix Self Check needs the command-line tools its instructions call (python and git). Our summary lists: Python 3.
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Fix Self Check is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Fix Self Check: Show Me Your Work Decision Log (cursor/plugins, 11k stars), Scope Creep Guard (lennney/stop-that-shit, 2.5k stars), Verification Before Completion (farm-fe/farm, 5.6k stars) and PUA High-Agency Governance (tanweai/pua, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Towow-ai (a GitHub organization) maintains it in Towow-ai/Flowness, which has 107 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on August 8, 2026.
Source: Towow-ai/Flowness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.