Not in the top 1,000 by GitHub stars
huisezhiyin/sdd-riper
Lightweight AI Agent Harness for agentic coding: let strong models explore while humans steer with minimal specs, checkpoints, approval, validation, and reverse sync.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/codemap/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
34ddbb954d00 → 34ddbb954d00
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 34ddbb954d00
No earlier version was observed for comparison.
skills/new-chat-ready/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
34ddbb954d00 → 34ddbb954d00
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 34ddbb954d00
No earlier version was observed for comparison.
skills/sdd-riper-one/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
34ddbb954d00 → 34ddbb954d00
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 34ddbb954d00
No earlier version was observed for comparison.
skills/sdd-riper-one-light/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
34ddbb954d00 → 34ddbb954d00
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 34ddbb954d00
No earlier version was observed for comparison.
Verified commit 34ddbb954d00d7ff666fa04c2843099207b0ea1a
git clone --filter=blob:none --no-checkout https://github.com/huisezhiyin/sdd-riper.git .hotskills/huisezhiyin-sdd-riper && git -C .hotskills/huisezhiyin-sdd-riper checkout --detach 34ddbb954d00d7ff666fa04c2843099207b0ea1a
# Copy each selected skill directory from .hotskills/huisezhiyin-sdd-riper into .agents/skills/<skill-name>/Heat
2.8- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- codemap
skills/codemap - new-chat-ready
skills/new-chat-ready - sdd-riper-one
skills/sdd-riper-one - sdd-riper-one-light
skills/sdd-riper-one-light
How it works
codemap
When your agent uses it
Generate, update, or drift-check agent-facing CodeMaps as progressive code terrain indexes for projects, features, capabilities, functions, modules, or bug chains. Use when Codex needs to inspect an unfamiliar codebase, map a feature/capability from entry to effect, create or update `mydocs/codemap/*`, answer `create_codemap`, `MAP`, `PROJECT MAP`, code terrain, impact-map, "where should the agent look first", check whether existing CodeMaps are stale after a diff, or prepare SDD-RIPER Research without loading the whole repository into context.
What it loads into context
Frontmatter
126 tokensAlways available to the agent
SKILL.md
881 tokensWhen the skill is activated
Reference documents
3,981 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Position
- Workflow
- Templates
- Output Rules
Files
SKILL.mdcore4,036 bytesSKILL.mdcore4,036 bytesSKILL.mdcore4,036 bytesSKILL.mdcore4,036 bytesagents/openai.yamlasset326 bytesreferences/drift-check.mddoc1,840 bytesreferences/feature-template.mddoc4,696 bytesreferences/principles.mddoc2,858 bytesreferences/project-template.mddoc5,111 bytesreferences/update-existing.mddoc1,429 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubnew-chat-ready
When your agent uses it
Prepare safe, compact new-chat handoffs when a user wants a fresh chat, resume pack, context reset, recovery, or agent handoff. Before creating a new conversation, preserve durable project knowledge and protect dirty Git work with a verified local snapshot branch and commit; optionally push that branch when explicitly authorized. Create the next Codex thread directly when supported, otherwise provide a paste-ready fallback prompt.
What it loads into context
Frontmatter
96 tokensAlways available to the agent
SKILL.md
2,234 tokensWhen the skill is activated
Reference documents
5,083 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Position
- Trigger
- Delivery Mode
- Workflow
- Output Rules
- References
Files
SKILL.mdcore10,761 bytesSKILL.mdcore10,761 bytesSKILL.mdcore10,761 bytesSKILL.mdcore10,761 bytesSKILL.mdcore10,761 bytesagents/openai.yamlasset458 bytesreferences/git-snapshot-protection.mddoc3,663 bytesreferences/handoff-template.mddoc3,218 bytesreferences/new-chat-prompt-template.mddoc2,195 bytesreferences/project-md-sync.mddoc5,805 bytesreferences/recovery-from-local-logs.mddoc5,433 bytesreferences/trigger-policy.mddoc3,076 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsdd-riper-one
When your agent uses it
将 SDD-RIPER 方法论落地为严格可执行流程的重型 Harness 技能。用于辅助用户澄清最终目标、生成 codemap/context、拆分最小混沌单元、维护完整 spec、执行 RIPER 阶段门禁、阻塞高风险动作和沉淀可 new chat 恢复的本地任务轨迹。
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
3,897 tokensWhen the skill is activated
Reference documents
29,306 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 全局行为与安全底线 (Global Safeguards)
- 核心定位
- Harness 教练职责
- 推荐流程（直接执行）
- 产物密度规则
- 上下文装配规则
- 按需能力入口
- 阶段约束（最小集合）
- 参考
Scripts executed separately
scripts/archive_builder.pyscripts/default_prompt_check.py
Files
README.mddoc14,547 bytesSKILL.mdcore14,628 bytesagents.mddoc320 bytesagents/openai.yamlasset927 bytesreferences/anti-context-decay.mddoc2,508 bytesreferences/archive-template.mddoc1,708 bytesreferences/commands.mddoc6,880 bytesreferences/default-prompt-setup.mddoc3,023 bytesreferences/minimum-chaos-unit.mddoc1,651 bytesreferences/mode-selection.mddoc2,149 bytesreferences/multi-project.mddoc2,849 bytesreferences/project-sync-boundary.mddoc3,038 bytesreferences/routing-map.mddoc1,994 bytesreferences/script-map.mddoc1,250 bytesreferences/sdd-riper-one-protocol.mddoc31,139 bytesreferences/skill-injection-check.mddoc2,595 bytesreferences/spec-template.mddoc12,075 bytesreferences/usage-examples.mddoc13,136 bytesreferences/water-flow.mddoc1,150 bytesreferences/workflow-quickref.mddoc6,941 bytesscripts/archive_builder.pyruns15,644 bytesscripts/default_prompt_check.pyruns7,406 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsdd-riper-one-light
When your agent uses it
面向 GPT-5.4 等强模型和熟练用户的轻量 AI Agent Harness / checkpoint-driven coding skill。默认用户已经把任务切到基本可执行的最小混沌单元；模型自行分解、探索与推进，人类通过最终目标、最小 spec、复述、checkpoint、证据验证与回写来低干扰控盘。
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
3,015 tokensWhen the skill is activated
Reference documents
13,422 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 核心定位
- 硬约束
- 默认假设
- 任务深度
- 最小工作流
- 何时暂停
- 按需模块
- 输出风格
Scripts executed separately
scripts/default_prompt_check.py
Files
README.mddoc7,217 bytesSKILL.mdcore11,674 bytesagents/openai.yamlasset842 bytesexamples/README.mddoc1,016 bytesexamples/codemap/codemap-feature-content-control.mddoc8,244 bytesexamples/specs/spec-light-runtime-compat.mddoc2,952 bytesexamples/specs/spec-standard-security-status-race.mddoc4,858 bytesreferences/anti-context-decay-lite.mddoc3,273 bytesreferences/conventions.mddoc2,843 bytesreferences/default-prompt-setup-lite.mddoc2,716 bytesreferences/mode-selection-lite.mddoc1,767 bytesreferences/modules.mddoc2,518 bytesreferences/project-sync-boundary.mddoc3,038 bytesreferences/routing-map.mddoc1,438 bytesreferences/script-map.mddoc944 bytesreferences/skill-injection-check.mddoc2,573 bytesreferences/spec-lite-template.mddoc4,026 bytesscripts/default_prompt_check.pyruns7,408 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- codemap
- new-chat-ready
- sdd-riper-one
- sdd-riper-one-light
Repository facts
- License
- No license detected
- Created
- Feb 25, 2026
- Last pushed
- Aug 28, 2026
- Forks
- 66
- Open issues
- 3
- Project activity
- Slowing
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 7 notes
skills/codemap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codemap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/codemap/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/new-chat-ready/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/new-chat-ready/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/new-chat-ready/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/new-chat-ready/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- No network access
- No hidden or obfuscated text
- No instruction overrides
- No access to secrets
- No requests to vote in Hot
Show all 3 signals by file
skills/sdd-riper-one-light/scripts/default_prompt_check.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/sdd-riper-one/scripts/archive_builder.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/sdd-riper-one/scripts/default_prompt_check.py
- Executable scriptline 1
#!/usr/bin/env python3
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 3 facts
- Executable script in code of a file that runssdd-riper-one-light/scripts/default_prompt_check.py:1High confidence
- Executable script in code of a file that runssdd-riper-one/scripts/archive_builder.py:1High confidence
- Executable script in code of a file that runssdd-riper-one/scripts/default_prompt_check.py:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/codemap/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/codemap/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/codemap/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/codemap/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/codemap/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
