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

No new commits yet today

Open the update feed

skill-based-architectureWoJiSama/skill-based-architecture

Provides an actionable architecture spec for writing AI agent skills (SKILL.md), solving bloated skill docs,…

No ratings yet Rate this skill
Stars610
Forks51
Watchers610
Open Issues1

InstallOne-line install

Installable · 17 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 WoJiSama/skill-based-architecture

17 more are not listed — run npx skills@latest add WoJiSama/skill-based-architecture --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

Provides an actionable architecture spec for writing AI agent skills (SKILL.md), solving bloated skill docs, mixed rules and flows, and agents failing to follow skills. Key capabilities include: 1. Single concise entry: SKILL.md keeps only description and trigger info under a dual budget so the agent can quickly decide whether to load the skill; 2. Rules vs flows separation: constraints go into rules/ and execution steps into workflow/, preventing rules from being drowned by procedures; 3. Progressive rigor and disclosure: content is loaded by task risk level and expanded only when needed, reducing context usage; 4. Gotchas first: gotchas are captured as the highest-value content to stop the agent from repeating mistakes; 5. Task execution and closure: defines execution and closing flow so outputs are verifiable with clear end conditions; 6. Durable records and self-maintenance: key conclusions must be persisted as durable records, with a mechanism for the skill to maintain itself; 7. Activation over storage: emphasizes the skill being correctly matched and activated in a session rather than merely stored; 8. Token efficiency: layered loading and concise wording compress the tokens a skill consumes.

TopicsTopics

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 ID1326
Data sourceGitHub
RepositoryWoJiSama/skill-based-architecture
CategoryAI & Agent Skills / Coding & Engineering Agent
Primary languageShell
LicenseMIT License
Default branchmain
GitHub repository ID1204572994
Node IDR_kgDOR8xTQg
Rank#1099 (position within the source ranking)
Site-wide popularity rank#1252 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02004006008002026-09-242026-10-112026-09-24 · 5962026-10-11 · 610
  • Now610
  • Previous point · 09-24 596
  • vs previous point +14
  • 2 data points 17 days
02040602026-09-242026-10-112026-09-24 · 492026-10-11 · 51
  • Now51
  • Previous point · 09-24 49
  • vs previous point +2
  • 2 data points 17 days

TimelineTimeline

Repository created2026-04-08 06:08:537 months ago
Data last updated2026-10-26 12:08:4921 days ago
Last commit2026-09-20 08:09:441 months ago

CommitLatest commit

Version [v1.15.1] committed by shiqi2021. Update Category: Bug Fixes & Stability Improvements. Commit details: fix: enforce upstream-changes archive policy and SKILL.md dual budget. This update resolves known runtime errors and enhances system reliability.

e5d2da5 v1.15.1 shiqi2021 2026-09-20

Next stepsNext steps