SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

repo-task-proof-loopDenisSergeevitch/repo-task-proof-loop

Turns a single repository development task into a closed loop of init-freeze-build-evidence-verify-fix-run-status,…

No ratings yet Rate this skill
Stars730
Forks47
Watchers730
Open Issues3

InstallOne-line install

Installable · 20 skills

This repository follows the Agent Skills spec, so one command installs it into your AI client — works across Claude Code, Codex, Cursor, Copilot, Windsurf, and 18+ other clients.

npx skills@latest add DenisSergeevitch/repo-task-proof-loop

20 more are not listed — run npx skills@latest add DenisSergeevitch/repo-task-proof-loop --list to see them all.

Add -g install globally (available in every project) · add --agent claude-code to target a client · add --yes to skip the prompts. Restart your AI client afterward and it will pick it up.

OverviewOverview

Key Features

Turns a single repository development task into a closed loop of init-freeze-build-evidence-verify-fix-run-status, forcing every step to leave checkable evidence so an agent cannot claim completion without proof. Key capabilities include: 1. Task initialization: init <TASK_ID> creates the workspace and task record for a given task, giving all later steps a single entry point; 2. Task freezing: freeze <TASK_ID> locks the task scope and acceptance criteria to prevent scope creep during execution; 3. Build and evidence: build <TASK_ID> triggers the build, and evidence <TASK_ID> collects build and run evidence so what changed and what ran becomes a traceable record; 4. Verification and fixing: verify <TASK_ID> judges whether the task meets the bar based on evidence, and fix <TASK_ID> enters a repair round that re-runs verification when it does not; 5. Run and status: run <TASK_ID> executes the task flow, and status <TASK_ID> shows which step the task is on and which evidence is still missing; 6. Reference and subagent conventions: references/REFERENCE.md and references/SUBAGENTS.md define commands, data structures and subagent collaboration rules so multi-step execution stays consistent.

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID1205
Data sourceGitHub
RepositoryDenisSergeevitch/repo-task-proof-loop
CategoryAI Engineering & Agent Development / Agent Workflow & Task Orchestration
Primary languagePython
LicenseApache License 2.0
Default branchmain
GitHub repository ID1188873672
Node IDR_kgDORtzFyA
Rank#973 (position within the source ranking)
Site-wide popularity rank#1103 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02004006008002026-09-232026-10-112026-09-23 · 7322026-10-11 · 730
  • Now730
  • Previous point · 09-23 732
  • vs previous point -2
  • 2 data points 18 days
02040602026-09-232026-10-112026-09-23 · 472026-10-11 · 47
  • Now47
  • Previous point · 09-23 47
  • vs previous point ±0
  • 2 data points 18 days

TimelineTimeline

Repository created2026-03-22 17:42:547 months ago
Data last updated2026-10-26 12:06:5221 days ago
Last commit2026-04-01 20:30:407 months ago

CommitLatest commit

Version [latest] committed by DenisSergeevitch. Update Category: Documentation & Guidelines Update. Commit details: Simplify README quick start and remove notes sections. This update improves usage instructions, deployment guides, and developer docs.

8536221 vlatest DenisSergeevitch 2026-04-01