Read references/project-intent.md for goals, audience, constraints, and maintenance posture.
Read references/project-map.md before navigating or editing files.
Read references/generated-files.md before modifying generated, vendored, lock, schema, snapshot, or build output files.
Load only the relevant detail references for the current task:
references/architecture.md
references/coding-standards.md
references/content-style.md
references/workflows.md
references/verification.md
references/release.md
Make changes in the repo's existing style.
Run the verification commands appropriate to the change and report any commands that could not be run.
Evaluation
The skill ships with an evaluation skeleton under references/evals/:
trigger-tests.md - requests that should and should not activate this skill
output-assertions.md - objective assertions about the final output
release-gate.md - release checklist (BLOCK/ALLOW) before sharing or publishing
Fill the tables with real project examples before relying on this skill in
production, and record pass/fail evidence after each run. Do not claim the skill
is release-ready until the release gate is all ALLOW with recorded evidence.
Evidence Discipline
Treat reference claims according to their labels:
observed_fact: repo evidence or command output.
declared_intent: maintainer preference or product goal.
recommended_standard: selected maintenance norm.
inferred_assumption: cautious assumption that may need confirmation.
When evidence conflicts, prefer observed facts for current repo behavior and declared intent for future direction.
1---2name: object-object-23description: [object Object]4---56# {{projectName}} Maintainer78## Workflow9101. Read `references/project-intent.md` for goals, audience, constraints, and maintenance posture.112. Read `references/project-map.md` before navigating or editing files.123. Read `references/generated-files.md` before modifying generated, vendored, lock, schema, snapshot, or build output files.134. Load only the relevant detail references for the current task:14 - `references/architecture.md`15 - `references/coding-standards.md`16 - `references/content-style.md`17 - `references/workflows.md`18 - `references/verification.md`19 - `references/release.md`205. Make changes in the repo's existing style.216. Run the verification commands appropriate to the change and report any commands that could not be run.2223## Evaluation2425The skill ships with an evaluation skeleton under `references/evals/`:2627- `trigger-tests.md` - requests that should and should not activate this skill28- `output-assertions.md` - objective assertions about the final output29- `release-gate.md` - release checklist (BLOCK/ALLOW) before sharing or publishing3031Fill the tables with real project examples before relying on this skill in32production, and record pass/fail evidence after each run. Do not claim the skill33is release-ready until the release gate is all ALLOW with recorded evidence.3435## Evidence Discipline3637Treat reference claims according to their labels:3839- `observed_fact`: repo evidence or command output.40- `declared_intent`: maintainer preference or product goal.41- `recommended_standard`: selected maintenance norm.42- `inferred_assumption`: cautious assumption that may need confirmation.4344When evidence conflicts, prefer observed facts for current repo behavior and declared intent for future direction.4546<!-- BEGIN USER RULES -->47<!-- Add durable project-specific rules here. This block is preserved on refresh. -->48<!-- END USER RULES -->
Run npx skillmds@latest add sscodeai/object-object-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
[object Object] It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
sscodeai (@sscodeai) published this skill. Their other Agent Skills are listed on their SkillMD profile.