Spec Aligning
- 1 installs
- 19 repo stars
- Updated March 1, 2026
- haowjy/orchestrate
Checks whether an implementation matches stated requirements and acceptance criteria, before implementation and before final sign-off.
About
Extracts key requirements from instructions, plans, and tests, then compares them against code and reports confirmed alignment, likely gaps, and unknowns. A developer uses it to sanity-check that the right thing was built and decide the next step.
- Compares requirements against code, tests, and reports
- Outputs aligned, misaligned, unknown, and next-step sections
Spec Aligning by the numbers
- 1 all-time installs (skills.sh)
- Ranked #2,476 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
- Data as of Aug 2, 2026 (Skillselion catalog sync)
npx skills add https://github.com/haowjy/orchestrate --skill spec-aligningAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1 |
|---|---|
| repo stars | ★ 19 |
| Last updated | March 1, 2026 |
| Repository | haowjy/orchestrate ↗ |
What it does
Checks whether an implementation matches stated requirements and acceptance criteria, before implementation and before final sign-off.
Files
Spec Alignment
Use this skill to sanity-check whether work matches intent.
When Invoked
Good fit when:
- requirements are spread across multiple messages/files;
- a large change needs a quick "did we build the right thing?" pass;
- review or test signals conflict on expected behavior.
Inputs
Use whichever requirement sources are available, typically:
- explicit user instructions;
- plan/spec docs (plans, ADRs, acceptance notes);
- tests that encode intended behavior;
- recent implementation/review reports.
If sources conflict, call that out and proceed with the most defensible interpretation.
Suggested Approach
Suggested flow (adapt as needed): 1. Extract the key requirements that matter for the decision at hand. 2. Compare those requirements against available evidence (code/tests/reports). 3. Identify confirmed alignment, likely gaps, and unresolved unknowns. 4. Propose the smallest next step to reduce uncertainty or close a gap.
Output
Keep output concise and decision-oriented. A short structure that often works:
- what appears aligned;
- what looks misaligned or risky;
- what is still unknown;
- what to do next.
Use explicit evidence when possible, but keep the format flexible for the task.
Related skills
Grill MeHave an agent relentlessly pressure-test their plan or design until every decision branch is resolved and shared understanding is reached.691k196kGrill With DocsPressure-test architecture decisions against their live codebase and living documentation before writing production code.585k196k
Lark CalendarLet their coding agents read, create, and manage events inside Lark (Feishu) Calendar directly from natural language instructions.493kLark ImLet their coding agent send instant notifications, post updates, and receive commands directly inside Lark (Feishu) workspaces.493kLark ContactLet their AI coding agents read and write contacts, send messages, and manage user data inside Lark (Feishu).493kLark AttendanceAutomatically fetch and report daily attendance data from Lark (Feishu) into their own tools or agents.493k