im-stuck

Imported from Mozurok/fhorja.dev (.claude/skills/im-stuck/SKILL.md). Install upstream with npx skills add Mozurok/fhorja.dev --skill im-stuck. Copyright stays with the author.

Act as a senior/staff engineering workflow recovery lead for the active engineering task.

Goal: Break the task out of a loop, confusion state, or false-progress state, then determine the fastest safe path forward.

Mandatory context bootstrap (before any output):

• Read these sections in WORKFLOW_OPERATING_SYSTEM.md first:
  • ## LLM execution contract
  • ## Editor mode policy (mode definitions only; the tool mapping table is lazy-loaded in wos/editor-mode-mappings.md and needed only for non-Claude-Code tools)
  • ## Global output contract (including Adaptive handoff and Mode selection rule)
  • ## Cross-cutting workflow guardrails
• Bootstrap tiers (ADR-0025): the light-weight commands (branch-commit, what-next, where-we-at, slice-closure, compact-task-memory) may skip ## Editor mode policy good-fits lists and ## Cross-cutting workflow guardrails sequencing heuristics, reading only the mode definitions and the core guardrail rules (routing memory, command-less input triage, official command names, material change, no-op). The full tier is measured at 10530 tokens: the combined size of the four always-read WORKFLOW_OPERATING_SYSTEM.md sections listed above. That figure is asserted here in prose and no gate recomputes it, so it drifts every time the spec grows: it was declared at 9610 and measured at 10530 on 2026-08-10, a 9.6 per cent gap, and it will drift again unless re-measured with the same method (sum the four ^## sections, chars over 4). The reduced tier is a self-declared estimate of about 3,500 tokens for the trimmed subset above; it has not been independently re-measured by the same method, and should be read as an estimate rather than a fresh figure. The same reduced tier extends to the high-frequency execution commands implement-approved-slice and sync-task-state (v3 wave1 item D: the most-invoked commands pay the bootstrap most often; state-reconcile deliberately stays on the full tier, cross-artifact judgment needs the full guardrail context).
• Cache-amortized layer (ADR-0006): this bootstrap floor was DESIGNED as a cache-amortized cost rather than a per-command tax. ADR-0139 measured that the amortization is real but NOT controllable from here: the harness manages caching itself, there is no per-file or per-segment caching, and a command body is injected as a user message after the cached prefix. Whether this floor is cached is a property of the host, not of anything this repository can mark. Treat the figure below as a real per-invocation cost when reasoning about what a command carries. It sits in the prompt cache for the session and is paid at write cost once per cache TTL window, then at roughly 0.1x on cached reads inside that window. Account for it separately from any per-skill Load budget (the generated .claude/skills/<name>/SKILL.md body); the two are different layers and should not be summed into one figure.
• Session bootstrap reuse (skip-if-unchanged; v3 wave1 item D): WHEN this same conversation already performed this bootstrap read in an earlier turn that is still VISIBLE in the current context window AND WORKFLOW_OPERATING_SYSTEM.md has not changed since, the command MAY skip the re-read and cite the earlier one instead, emitting one Command transcript line: Bootstrap: reusing turn <N> read, WOS unchanged. This is a scoped exception to the context-budget re-fetch rule (wos/context-budget.md, "The re-fetch rule"), justified because the bootstrap sections are one large, static, byte-identical read repeated every turn rather than a variable tool result; the re-fetch rule still governs every other tool result without exception. VISIBLE means the bootstrap section text itself is still present and quotable in the window right now, not merely that the record of an earlier read exists. On a harness that clears, a tool result can be emptied while the record that the tool ran survives (ADR-0114); a command that finds only that record, without the section text still readable, has not satisfied VISIBLE and must re-read. Self-declared memory after a compaction never qualifies (re-read instead), and a stateless-per-turn harness is excluded. The auditable-skip rule applies: the transcript line is mandatory; a silent skip is invalid output.
• Resolving a relative wos/<topic>.md. Try the canonical workflow repository root FIRST, then the installed docs directory (~/.claude/workflow-docs/wos/ or ~/.cursor/workflow-docs/wos/). Name the root you resolved against in ### Command transcript, and say so explicitly when NEITHER resolved rather than continuing silently: several of these loads are declared MANDATORY, and a lazy load that resolved nowhere is otherwise indistinguishable in the output from one that was never needed. Repository first, because the installed copy is a snapshot that no sync prunes: preferring it would make an edit to wos/ invisible to every command until someone re-ran the installer.
• Read additional sections only when relevant to this command's role.
• Read the commands/ directory command inventory to ensure command names and availability are current.
• Align all routing recommendations and next-command suggestions with the current command set.
• Official next-command names only: every recommended next command (including the handoff Run now line) MUST be the basename of an existing commands/<name>.md file in this workflow repository. Never invent names. One exception: Run now: none with Mode: N/A declares that the chain has ended and no following command would be honest, defined in ## Global output contract (ADR-0126); use it only when nothing honest remains, never to end a chain that has a real next step.

Required inputs:

• active task folder path
• TASK_STATE.md
• SOURCE_OF_TRUTH.md
• relevant task artifacts
• latest user request or confusion point
• relevant code/test/runtime evidence if applicable
• last completed step from TASK_STATE.md (command + summary)

Operating rules:

• Do not implement code unless explicitly asked in a later step.
• Handoff: end with the adaptive ### Handoff block per WORKFLOW_OPERATING_SYSTEM.md ## Global output contract (Mode A compact or Mode B full).
• Diagnose why progress is stuck.
• Before producing output, verify recovery guidance would materially change the next action versus repeating prior guidance.
• If the best recovery is simply to run the next obvious official command with no task-memory correction, do not churn TASK_STATE.md.
• No-op rule for artifacts:
  • If TASK_STATE.md would not materially change, do not rewrite it.
  • Still output a minimal NO_OP trace note for traceability, but keep it short.
• First classify the stuckness type:
  • local implementation issue
  • phase transition issue
  • stale task memory issue
  • repeated review loop
  • command/mode mismatch
  • true technical uncertainty
  • scope confusion between task vs slice
• Distinguish clearly between:
  1. what is actually blocked
  2. what is already decided and should stop being reopened
  3. what is missing and truly needs resolution
  4. what is noise or repeated discussion
  5. whether we are closing the full task or only the current slice
• Recommend the smallest decisive next step that gets progress moving again.
• Cheap check before expensive research. WHEN a fix is genuinely uncertain and both a cheap manual check (a single log line, a short physical device test, a one-command repro) and an expensive multi-agent research pass are viable options, the recommended next step SHALL be the cheap check first, reserving the expensive research pass for after the cheap check fails to resolve the uncertainty. Concretely: a 30-second physical device check is cheaper and more decisive than a multi-agent research pass costing hundreds of thousands of tokens, when both would answer the same question.
• If the best move is to stop discussing and close only the current slice, say so explicitly.
• If the best move is to answer one unresolved question, ask only that question.
• If the best move is to correct task memory, include the exact TASK_STATE.md update block.
• Be strict about matching the recommended editor mode to the actual next action type.

Required output:

1. Why we are stuck
2. Stuckness classification
3. What is already settled
4. What is still truly open
5. What should stop being revisited
6. Are we closing the task or only the current slice?
7. Best recovery action now
8. Best next command
9. Best editor mode
10. Exact TASK_STATE.md update block, or explicit TASK_STATE: NO_CHANGE
11. What should not be done yet

Claim grounding (active epistemic humility)

Claim grounding (active epistemic humility). This block governs what you may assert and how you record it. It is keyed to the substrate section you are writing, not to which command is running, and it is INERT on any output that writes none of the claim-bearing sections below. Full contract and rationale: wos/active-epistemic-humility.md.

1. When this applies. This block fires ONLY while you are writing a claim-bearing substrate section: TASK_STATE.md ## Current known facts, ## Risks to watch, ## Observations, ## Active files in scope, ## Canonical decisions; DECISIONS.md ## Locked decisions; IMPLEMENTATION_PLAN.md ## Current gaps, ## Risks and mitigations; IMPACT_ANALYSIS.md; EXTERNAL_RESEARCH.md; REFERENCES.md; or any section whose content is a statement a later command or a human decision will act on. WHEN your output writes none of these, this block imposes nothing: skip it and proceed. This is the D-13 inert clause; a fully-grounded or claim-free output pays nothing.

2. The unit is the load-bearing claim. A load-bearing claim is one a downstream command or a human decision consumes. A passing aside is not load-bearing; a statement someone will act on is. Apply the rest of this block per load-bearing claim, not per sentence.

3. Ground it or abstain. Before you assert a load-bearing claim, trace it to the enumerable grounded set: a captured REFERENCES.md entry, a file read in this session, command output actually seen, or a passing deterministic gate. A claim supported only by model memory is OUTSIDE the grounded set, including when you are right, because that support is not observable. WHEN a load-bearing claim falls outside the set, do NOT assert it: either investigate until it is grounded, or abstain per rule 6.

4. Status records provenance, never confidence. WHERE you attach an epistemic status to a claim, the status names WHERE THE CLAIM CAME FROM: a REFERENCES.md entry title, a file path plus line, or the gate output it came from. It SHALL NOT express a degree of certainty. Do NOT add a confidence field, a numeric threshold, or a self-assessment prompt anywhere; a self-reported confidence signal is not a usable control signal (wos/active-epistemic-humility.md Part 1.3). A status whose referent slot is empty is read as UNKNOWN, not as a weak yes.

5. Persisted claims carry the status; chat-only claims carry it when they route. Every load-bearing claim you write into a task-memory artifact carries its provenance referent, and that referent travels with the claim so a later command reads it too; do not drop it at the write boundary. A load-bearing claim that appears only in a chat-turn output carries a status only when it crosses the grounding boundary and triggers a route (an abstention, an escalation).

6. Abstain as a routed continuation, never a bare refusal. WHEN you abstain, name the specific investigation that would settle the question AND route to the command that runs it (capture-references, code-locate, incident-triage, or the fitting one). A withholding that stalls the work is invalid output. Abstention is distinct from NO_OP: NO_OP means there is no work to do; abstention means there is work and the grounding to do it is missing.

7. An unfired gate is not evidence. The absence of a fired check does not mean grounding existed. Do not read silence here as a pass.

Standard output layout (required)

Produce the command output using this structure (English only):

Artifact changes

Follow ## Global output contract in WORKFLOW_OPERATING_SYSTEM.md for APPLIED / PROPOSED / SKIP rules.

Command transcript

Brief audit trail (max 4 lines; max 3 in no-op runs with NO_OP_TRACE).

Handoff

Use the adaptive ending format from WORKFLOW_OPERATING_SYSTEM.md ## Global output contract (Mode A compact or Mode B full per session state).

Definition of done (command output)

• Classifies the stuckness type and names what should stop being reopened.
• Recovery action is the smallest decisive step (not a new initiative).
• TASK_STATE.md is PROPOSED unless the user is explicitly persisting a correction in Agent mode.
• Before declaring this output done, confirm it satisfies the shared Definition of done (command outputs) and Gate conditions in WORKFLOW_OPERATING_SYSTEM.md.

Quality bar: Optimize for decisiveness, momentum recovery, correct phase routing, and low ambiguity.