Openspec ship change
Skill TheSmuks/openspec-hermes/skills/openspec/openspec-ship-change
Use when working with OpenSpec in Hermes: take an existing OpenSpec change from current state through remaining planning, apply, verify, and archive.From its SKILL.md
npx -y skills add TheSmuks/openspec-hermes --skill openspec-ship-changeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.2 KB, 402 tokens by cl100k_base, as published. Nobody here has run it
openspec-ship-change
Use this for an already-created OpenSpec change that should be finished automatically from wherever it currently is.
Flow:
detect state -> fill missing planning -> apply remaining tasks -> verify -> archive when safe
Ground rules
- Work from the user's project root. If unknown, inspect the current directory first.
- Ensure OpenSpec exists with
openspec --version. If missing, install it withnpm install -g @fission-ai/openspec@latest. - If
openspec/is missing, initialize withopenspec init --tools none. - Use OpenSpec CLI state as source of truth:
openspec list --json,openspec status --change <id> --json,openspec instructions <artifact> --change <id> --json,openspec validate <id>. - Do not stop at a plan. Create artifacts, implement code, run checks, update task checkboxes, and report real command output.
- Ask only when a real decision changes the work. Otherwise choose the recommended default and proceed.
Procedure
- Identify the change. If not specified, run
openspec list --jsonand infer only if unambiguous. - Inspect
openspec status --change <name> --jsonand existing artifacts. - If planning artifacts are missing, create ready artifacts using
openspec instructions <artifact> --change <name> --jsonuntil apply prerequisites are complete. - If tasks are incomplete, implement remaining unchecked tasks and update
tasks.mdas each task is verified. - Run relevant project checks and
openspec validate <name>. - Verify implementation evidence for every requirement and scenario.
- Archive with
openspec archive <name> --yesonly when safe or explicitly requested. - Report exactly what was completed and any blockers left active.
Use this when work was interrupted, partially planned, or partially implemented.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most ship operate skills give in 402 tokens
Counted across 779 of the 1,178 authors here whose files we hold, read 2026-08-07
- Document a rollback plan before deploymentin 41 of 779, across 22 files
- Update the changelogin 21 of 779, across 19 files
- Run the test suitein 20 of 779
- Create an annotated git tagin 20 of 779
- Clean up feature flags after full rolloutin 18 of 779, across 10 files
- Verify deployment health after launchin 18 of 779, across 10 files
- Test both feature flag statesin 17 of 779, across 9 files
- Verify the working tree is cleanin 17 of 779
- Make database migrations backward-compatiblein 16 of 779, across 8 files
- Set up error monitoring before launchin 15 of 779, across 7 files
- Monitor metrics at each rollout stagein 14 of 779, across 5 files
- Create a GitHub releasein 14 of 779
Said here and by no other author read
- work from the user's project root
- ensure openspec exists or install it
- initialize openspec if the directory is missing
- use openspec cli state as the source of truth
- implement remaining unchecked tasks
- update tasks.md as each task is verified
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.