skills: add portable continue and status session-discipline skills

README.md

@@ -113,6 +113,7 @@ ongoing host installs and upgrades.
 | `address-review` | Fetch and triage GitHub PR review comments. |
 | `adversarial-pr-review` | Run a skeptical pre-merge or post-merge PR review. |
 | `autoreview` | Run a structured second-model local diff review. |
+| `continue` | Resume an in-progress task with a structured checkpoint. |
 | `evaluate-issue` | Decide whether an issue or proposed fix is worth doing. |
 | `plan-issue-triage` | Produce a ready prompt for review-only issue triage. |
 | `plan-pr-batch` | Shape candidate issues or PRs before launching a batch. |
@@ -121,6 +122,7 @@ ongoing host installs and upgrades.
 | `replicate-ci` | Reproduce hosted-CI/local parity gaps. |
 | `run-ci` | Choose and run repo-local CI checks. |
 | `spec` | Turn vague implementation intent into requirements, design, and tasks. |
+| `status` | Report tight progress (done/in-progress/blocked/next) without starting new work. |
 | `tdd` | Drive test-first red-green-refactor loops for features and bug fixes. |
 | `triage` | Build a whole-surface issue/PR inventory and batch split. |
 | `update-changelog` | Classify merged PRs and update a repo changelog. |

skills/continue/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: continue
+description: Resume an in-progress task with a structured checkpoint instead of a bare "continue", re-establishing what is done, what is next, and how done is verified. Use when resuming work after an interruption, handoff, or a vague "keep going".
+argument-hint: '[focus text or scope]'
+---
+
+# Continue
+
+Resume the current task. Before doing any new work, re-establish context so work does not drift or
+repeat:
+
+1. **Repo rules** - Read `AGENTS.md` first so repo-specific commands, formatting, boundaries, and
+   safety rules are current before acting.
+2. **Where we are** - Summarize in 2-4 lines what is already done (cite files, commits, PRs, issues,
+   or linked planning docs) and the current goal. If there is no task currently in progress (no prior
+   conversation, no staged work, no recent commits on this branch, and no open PR or issue context),
+   say so and ask the user what to continue instead of inferring a goal. If the goal is unclear but
+   prior work exists, state your best inference and proceed only when confidence is reasonable; for
+   low-confidence inference, state the hypothesis and ask the user to confirm before acting.
+3. **What is next** - List the remaining steps to reach done, then pick the next concrete one.
+4. **Definition of done** - Restate the overall success criteria in one line, plus the command or
+   test that will verify it. If there is no runnable check, state how completion will be confirmed.
+5. Continue working on **that one next step only**. Stop after completing it.
+
+If the user supplied focus text or arguments, treat it as additional direction or a narrowed scope
+for what to continue.
+
+- Do not re-do completed work, and do not ask the user to repeat context you can reconstruct from
+  the conversation, open files, or git state.
+- Honor `AGENTS.md` boundaries and safety rules while resuming; never push or take irreversible
+  actions unless the task already authorized them.
+- End with a `$status` report when that companion skill is installed; otherwise use the same four
+  sections directly: Done, In progress, Blocked / needs input, and Next. Treat this closing summary
+  as a report of the resumed work, not as a separate trigger to start additional work beyond step 5.

skills/status/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: status
+description: Report tight progress on the current work - done, in progress, blocked, and next - without starting new work. Use when asked for a status update or "where are we / anything needed from me".
+---
+
+# Status
+
+Give a tight status update on the current work. **Do not start new work.**
+
+Report:
+
+- **Done** - what is complete. Note whether it has been verified, cite the check result when one
+  exists, or mark it as done and awaiting verification when a check has not run yet.
+- **In progress** - what is mid-way through.
+- **Blocked / needs input** - anything that genuinely needs a decision, credentials, or an external
+  unblock. If nothing, say "nothing blocked".
+- **Next** - the next one to three concrete steps, without starting them.
+
+Keep it concise: one to three lines per section. If you are waiting on a long-running command or a
+background agent, name it and the signal you are waiting for. Do not start new long-running work
+solely to produce a richer status report.