ds-project-resume
Skill20 starsChanged 46 days agoMITView on GitHub
Read .project/ state and report where to pick up.
In this repository52 other files it gives its agents.
- ds-dev-skill-benchSkill
- ds-agent-reviewSkill
- ds-architecture-planSkill
- ds-arenaSkill
- ds-blast-radiusSkill
- ds-blueprintSkill
- ds-bug-reviewSkill
- ds-clarity-reviewSkill
- ds-code-quality-reviewSkill
- ds-comment-reviewSkill
- ds-data-modeSkill
- ds-data-reviewSkill
- ds-debugSkill
- ds-deslopSkill
- ds-doc-quality-reviewSkill
- ds-exploreSkill
- ds-git-modeSkill
- ds-go-reviewSkill
- ds-grill-meSkill
- ds-handoffSkill
- ds-howSkill
- ds-humanizeSkill
- ds-interaction-modeSkill
- ds-java-reviewSkill
- ds-notebook-reviewSkill
- ds-onboardingSkill
- ds-osvSkill
- ds-perf-planSkill
- ds-project-checkpointSkill
- ds-python-reviewSkill
- ds-quality-gateSkill
- ds-reflectSkill
- ds-retroSkill
- ds-roadmapSkill
- ds-rust-reviewSkill
- ds-security-reviewSkill
- ds-semgrepSkill
- ds-shell-reviewSkill
- dsSkill
- ds-specSkill
- ds-step-modeSkill
- ds-tdd-modeSkill
- ds-test-modeSkill
- ds-test-quality-reviewSkill
- ds-tiger-style-modeSkill
- ds-tldtSkill
- ds-ts-reviewSkill
- ds-ui-modeSkill
- ds-ui-quality-reviewSkill
- ds-verify-thisSkill
- ds-zig-reviewSkill
- ds-zoom-outSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
When invoked, load the project's state and report where to pick up — the counterpart to /ds-project-checkpoint.
- Very specific: line 16
Read .project/state.md. If it is absent, say so, suggest /ds-project-checkpoint, and stop.
- Very specific: line 22
Report the file, not around it: No git, no counts, no branch position, no observations about the repo.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
When invoked, load the project's state and report where to pick up — the counterpart to /ds-project-checkpoint. Safe to run at the start of any session. It writes nothing.
Arguments
--no-modes— read.project/config.mdbut don't apply what it lists. Still name the modes it configures, so opting out never hides them.
Process
- Apply the modes in
.project/config.md. For each one, read that mode'sSKILL.mdfrom your assistant's skills directory (~/.claude/skills/,$CLAUDE_CONFIG_DIR/skills/,~/.codex/skills/,~/.config/opencode/skills/) and adopt its rules for the session. Each mode ends with its own confirmation line — those are the echo; don't restate the list as prose. Where a mode grants a standing authorization, name it inline on that line. If a listed mode isn't installed, say so and tell the user to apply it by hand — never skip one silently. - Read
.project/state.md. If it is absent, say so, suggest/ds-project-checkpoint, and stop. - Report the mode confirmations, then
# now, then# next.
Rules
- Two sections are reported, two are loaded.
# nowand# nextare the report.# settledand# hazardsenter context so they govern what you do — never say them back to the person who wrote them. Name one only when it changed what you did: "that probe is load-bearing, so I left it." - Report the file, not around it. No git, no counts, no branch position, no observations about the repo. A fact
state.mddoesn't hold is not part of the report, however useful it looks. - Modes come first. A standing authorization read out after the work context is backwards.
Output
Mode confirmations, # now, # next. Usually four lines.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

