Skip to main content
在 Manus 中运行任何 Skill
一键导入
softwaresalt
GitHub 创作者资料

softwaresalt

按仓库查看 6 个 GitHub 仓库中的 106 个已收集 skills。

已收集 skills
106
仓库
6
更新
2026-07-14
仓库浏览

仓库与代表性 skills

build-feature
软件开发工程师

Usage: Build feature {spec-name} phase {phase-number}. Implements a single phase from the spec's task plan, iterating build-test cycles until the phase passes its constitution gate, then records memory, logs decisions, and commits.

2026-05-21
acquire-codebase-knowledge
软件开发工程师

Use this skill when the user asks to map, document, or onboard into an existing codebase. Produces structured documentation covering stack, structure, architecture, conventions, integrations, testing, and concerns. Only documents what is verifiable from files or terminal output — never infers or assumes.

2026-05-21
brainstorming
项目管理专家

Use before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design through collaborative dialogue before implementation.

2026-05-21
browser-automation
软件开发工程师

Browser automation skill. Drives agent-browser through structured navigate→snapshot→interact→re-snapshot flows with authentication support, form automation, visual verification, and explicit human checkpoints for external flows.

2026-05-21
changelog-generator
软件开发工程师

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes.

2026-05-21
debugging
软件开发工程师

Systematic root-cause debugging with verification. Use for errors, stack traces, broken tests, flaky tests, regressions, or anything not working as expected.

2026-05-21
document-review
项目管理专家

Structural review of documents for gaps, clarity, completeness, and organization. Use when a brainstorm, plan, spec, ADR, or any doc needs polish before the next workflow step.

2026-05-21
harness-architect
软件开发工程师

Scaffolds compilable but failing test harnesses for feature and chore tasks

2026-05-21
当前展示该仓库 Top 8 / 33 个已收集 skills。
spike
软件开发工程师

Time-boxed investigation of a technical question, feasibility study, or proof-of-concept — produces a findings artifact with a recommendation and optional backlog linkage

2026-07-14
spike
软件开发工程师

Time-boxed investigation of a technical question, feasibility study, or proof-of-concept — produces a findings artifact with a recommendation and optional backlog linkage

2026-07-13
build-feature
软件开发工程师

Usage: Build feature {task-id} with harness {harness-cmd}. Implements a requested feature by continuously looping a fast worker agent against a strict, passing-import but failing test harness until success is achieved.

2026-07-13
compound-refresh
软件开发工程师

Review and maintain institutional learnings in docs/compound/ so the compound library stays accurate, deduplicated, and evidence-backed

2026-07-13
plan-harden
软件开发工程师

Risk-triggered plan reinforcement that deepens verification, rollback, and guardrail detail before plan review

2026-07-13
pr-lifecycle
软件开发工程师

Manages the full PR lifecycle: creation, review comment handling, CI remediation, and user-approved merge

2026-07-08
review
软件质量保证分析师与测试员

Structured code review using tiered persona subagents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR, as a build gate, or for standalone review.

2026-07-08
harvest
项目管理专家

Decomposes a reviewed implementation plan into backlog feature/task/subtask hierarchy

2026-07-03
当前展示该仓库 Top 8 / 30 个已收集 skills。
browser-automation
软件开发工程师

Browser automation skill. Drives agent-browser through structured navigate→snapshot→interact→re-snapshot flows with authentication support, form automation, visual verification, and explicit human checkpoints for external flows.

2026-06-28
iterative-experiment
软件开发工程师

Autonomous iterative experimentation loop. Defines a measurable goal, establishes a baseline, then iterates modify→commit→measure→keep/revert until the goal is met or the budget is exhausted. Persists a TSV experiment log under the configured results directory.

2026-06-28
shipment-reconcile
软件开发工程师

GI/GR reconciliation gate for shipment manifests — verifies every manifest item exists in queue (pre-mode) or archive (post-mode) with the expected status before or after backlogit_ship_shipment runs.

2026-06-28
harness-doctor
软件开发工程师

On-demand harness health diagnostic. Checks manifest presence, version drift, file integrity, cross-reference validity, MCP tool availability, and template variable residue. Produces a per-category graded health report.

2026-06-28
security-audit
信息安全分析师

Multi-phase security audit skill. Scans agentic config surfaces and application source for OWASP Top 10 vulnerabilities, STRIDE threats, and config hygiene issues. Produces a scored, graded report persisted to the configured security docs directory (default: docs/security).

2026-06-28
harness-architect
软件质量保证分析师与测试员

Scaffolds compilable but failing test harnesses for feature and chore tasks

2026-04-14
harvest
项目管理专家

Decomposes a reviewed implementation plan into backlog feature/task/subtask hierarchy

2026-04-14
plan-review
软件开发工程师

Multi-persona review gate for implementation plans. Validates architectural soundness, scope boundaries, and coding standards compliance before the harvest skill decomposes a plan into work items.

2026-04-14
当前展示该仓库 Top 8 / 17 个已收集 skills。
harness-architect
软件质量保证分析师与测试员

Scaffolds compilable but failing test harnesses for feature and chore tasks

2026-05-11
review
软件质量保证分析师与测试员

Structured code review using tiered persona subagents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR, as a build gate, or for standalone review.

2026-05-11
harness-doctor
软件质量保证分析师与测试员

On-demand harness health diagnostic. Checks manifest presence, version drift, file integrity, cross-reference validity, MCP tool availability, and template variable residue. Produces a per-category graded health report.

2026-05-11
harvest
项目管理专家

Decomposes a reviewed implementation plan into backlog feature/task/subtask hierarchy

2026-05-11
plan-review
项目管理专家

Multi-persona review gate for implementation plans. Validates architectural soundness, scope boundaries, and coding standards compliance before the harvest skill decomposes a plan into work items.

2026-05-11
security-audit
信息安全分析师

Multi-phase security audit skill. Scans agentic config surfaces and application source for OWASP Top 10 vulnerabilities, STRIDE threats, and config hygiene issues. Produces a scored, graded report persisted to the configured security docs directory (default: docs/security).

2026-05-11
pr-lifecycle
软件开发工程师

Manages the full PR lifecycle: creation, review comment handling, CI remediation, and user-approved merge

2026-04-26
compact-context
软件开发工程师

Scan .copilot-tracking/ for stale or oversized tracking artifacts, produce compacted summaries, and archive originals. Use when tracking files accumulate beyond thresholds that degrade agent context quality.

2026-03-29
当前展示该仓库 Top 8 / 12 个已收集 skills。
iterative-experiment
软件开发工程师

Autonomous iterative experimentation loop. Defines a measurable goal, establishes a baseline, then iterates modify→commit→measure→keep/revert until the goal is met or the budget is exhausted. Persists a TSV experiment log under the configured results directory.

2026-05-30
harness-architect
软件质量保证分析师与测试员

Scaffolds compilable but failing test harnesses for feature and chore tasks

2026-05-30
harness-doctor
软件质量保证分析师与测试员

On-demand harness health diagnostic. Checks manifest presence, version drift, file integrity, cross-reference validity, MCP tool availability, and template variable residue. Produces a per-category graded health report.

2026-05-30
harvest
软件开发工程师

Decomposes a reviewed implementation plan into backlog feature/task/subtask hierarchy

2026-05-30
plan-review
软件开发工程师

Multi-persona review gate for implementation plans. Validates architectural soundness, scope boundaries, and coding standards compliance before the harvest skill decomposes a plan into work items.

2026-05-30
review
软件质量保证分析师与测试员

Structured code review using tiered persona subagents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR, as a build gate, or for standalone review.

2026-05-30
security-audit
信息安全分析师

Multi-phase security audit skill. Scans agentic config surfaces and application source for OWASP Top 10 vulnerabilities, STRIDE threats, and config hygiene issues. Produces a scored, graded report persisted to the configured security docs directory (default: docs/security).

2026-05-30
shipment-reconcile
软件开发工程师

GI/GR reconciliation gate for shipment manifests — verifies every manifest item exists in queue (pre-mode) or archive (post-mode) with the expected status before or after backlogit_ship_shipment runs.

2026-05-30
harness-architect
软件质量保证分析师与测试员

Scaffolds compilable but failing test harnesses for feature and chore tasks

2026-07-09
review
软件质量保证分析师与测试员

Structured code review using tiered persona subagents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR, as a build gate, or for standalone review.

2026-07-09
pr-lifecycle
软件开发工程师

Manages the full PR lifecycle: creation, review comment handling, CI remediation, and user-approved merge

2026-07-09
shipment-reconcile
软件开发工程师

GI/GR reconciliation gate for shipment manifests — verifies every manifest item exists in queue (pre-mode) or archive (post-mode) with the expected status, and closes shipments with the single-artifact safe-close procedure that archives ONLY manifest item IDs with a verify-after-each invariant + git-revert-on-cascade instead of the destructive cascade backlogit_ship_shipment.

2026-07-09
harness-doctor
软件质量保证分析师与测试员

On-demand harness health diagnostic. Checks manifest presence, version drift, file integrity, cross-reference validity, MCP tool availability, and template variable residue. Produces a per-category graded health report.

2026-07-09
security-audit
信息安全分析师

Multi-phase security audit skill. Scans agentic config surfaces and application source for OWASP Top 10 vulnerabilities, STRIDE threats, and config hygiene issues. Produces a scored, graded report persisted to the configured security docs directory (default: docs/security).

2026-05-20
已展示 6 / 6 个仓库
已展示全部仓库