ABINIT Workflows
This skill handles practical ABINIT workflows for setup, review, and recovery. Use it when the request is specifically about ABINIT, .abi inputs, multi-dataset runs, pseudopotential handling, convergence choices, or reading .abo-style outputs.
When to use
Use this skill when the user mentions or implies:
ABINIT, .abi, .abo, abinit, abiinput, or multi-dataset inputs
- ground-state, geometry optimization, DOS, band structure, or restart workflows in ABINIT
ecut, ngkpt, shiftk, nshiftk, tolvrs, toldfe, ndtset, getwfk, irdwfk, or irdden
- pseudos, scheduler scripts, walltime planning, or restart files such as
DEN, WFK, and HIST
Operating stance
Prioritize missing information in this order:
- target task:
gs, relax, dos, band, or restart
- pseudopotential family and exchange-correlation consistency
- basis and k-point controls:
ecut, ngkpt, shiftk, and stopping criteria
- parent-child file flow: which stage produces
DEN, WFK, or geometry for the next stage
- scheduler and MPI layout
Never silently invent:
- pseudopotential filenames or versions
- whether the calculation should be metallic, spin-polarized, or
+U
- a high-symmetry path without a real source
- whether an old
WFK or DEN file is scientifically safe to reuse
Workflow
1. Classify the request
- Setup: generate one stage or a staged directory layout.
- Review: inspect an existing ABINIT directory and summarize status.
- Recovery: explain the likely failure mode and recommend the smallest safe restart.
2. Gather the minimum viable context
Before making code-specific recommendations, establish:
- structure source and whether the cell is bulk, slab, or molecule-in-box
- pseudopotential family and intended functional
- whether the system is metallic, magnetic, or unknown
- target observable: relaxed geometry, total energy, DOS, or band plot
- scheduler environment and expected walltime
3. Use the bundled helpers
scripts/make_abinit_inputs.py
Generate conservative gs, relax, nscf, dos, or band workflow skeletons.
scripts/check_abinit_job.py
Check an ABINIT directory for missing inputs, restart dependencies, and obvious pseudo-path issues.
scripts/summarize_abinit_run.py
Summarize an ABINIT directory or .abo output using simple, auditable heuristics.
scripts/recommend_abinit_recovery.py
Turn incomplete or broken ABINIT stages into concrete restart and parent-child recovery guidance.
scripts/export_status_report.py
Export a shareable markdown status report from an ABINIT run or staged workflow.
scripts/export_input_suggestions.py
Export conservative ABINIT input snippets based on detected recovery patterns.
4. Load focused references only when needed
- ABINIT-specific workflow guidance:
references/abinit.md
- convergence planning:
references/convergence.md
- failures and restarts:
references/failure-modes.md
- scheduler considerations:
references/schedulers.md
5. Deliver an auditable answer
Whenever you recommend settings or restart changes, include:
- the task and parent-child stage assumption
- unresolved physics choices the user still needs to confirm
- exact files that were created or edited
- what output or artifact must exist before the next stage can run
Task guardrails
Ground-state and relaxation
- Keep exploratory relaxations numerically sane but not over-tight.
- Separate geometry convergence from production-quality total energies.
- Do not compare final energies from a loose relaxation against a tighter static setup without rerunning consistently.
DOS
- Treat DOS as a child workflow that depends on a trustworthy parent state.
- Use denser k-point sampling for DOS than for a cheap exploratory relaxation.
- Be explicit about whether the stage reads
DEN, WFK, or both.
Band structure
- Require a converged parent stage.
- Do not fabricate a band path; use a symmetry tool or literature reference.
- Keep the band stage read-only with respect to density whenever possible.
Quality bar
- Prefer conservative defaults over flashy guesses.
- Distinguish ABINIT-specific syntax advice from material-specific physics advice.
- Point out when a recommendation is only a heuristic.
- If the output is incomplete or the pseudo policy is unclear, say so directly.
1---2name: abinit-workflows3description: Use when the task involves ABINIT electronic-structure workflows, including .abi input preparation, gs, relax, nscf, DOS, and band setups, pseudopotential and dataset organization, convergence review, restart handling with DEN or WFK files, output diagnosis, and scheduler scripts.4---56# ABINIT Workflows78This skill handles practical ABINIT workflows for setup, review, and recovery. Use it when the request is specifically about `ABINIT`, `.abi` inputs, multi-dataset runs, pseudopotential handling, convergence choices, or reading `.abo`-style outputs.910## When to use1112Use this skill when the user mentions or implies:1314- `ABINIT`, `.abi`, `.abo`, `abinit`, `abiinput`, or multi-dataset inputs15- ground-state, geometry optimization, DOS, band structure, or restart workflows in ABINIT16- `ecut`, `ngkpt`, `shiftk`, `nshiftk`, `tolvrs`, `toldfe`, `ndtset`, `getwfk`, `irdwfk`, or `irdden`17- pseudos, scheduler scripts, walltime planning, or restart files such as `DEN`, `WFK`, and `HIST`1819## Operating stance2021Prioritize missing information in this order:22231. target task: `gs`, `relax`, `dos`, `band`, or restart242. pseudopotential family and exchange-correlation consistency253. basis and k-point controls: `ecut`, `ngkpt`, `shiftk`, and stopping criteria264. parent-child file flow: which stage produces `DEN`, `WFK`, or geometry for the next stage275. scheduler and MPI layout2829Never silently invent:3031- pseudopotential filenames or versions32- whether the calculation should be metallic, spin-polarized, or `+U`33- a high-symmetry path without a real source34- whether an old `WFK` or `DEN` file is scientifically safe to reuse3536## Workflow3738### 1. Classify the request3940- **Setup**: generate one stage or a staged directory layout.41- **Review**: inspect an existing ABINIT directory and summarize status.42- **Recovery**: explain the likely failure mode and recommend the smallest safe restart.4344### 2. Gather the minimum viable context4546Before making code-specific recommendations, establish:4748- structure source and whether the cell is bulk, slab, or molecule-in-box49- pseudopotential family and intended functional50- whether the system is metallic, magnetic, or unknown51- target observable: relaxed geometry, total energy, DOS, or band plot52- scheduler environment and expected walltime5354### 3. Use the bundled helpers5556- `scripts/make_abinit_inputs.py`57 Generate conservative `gs`, `relax`, `nscf`, `dos`, or `band` workflow skeletons.58- `scripts/check_abinit_job.py`59 Check an ABINIT directory for missing inputs, restart dependencies, and obvious pseudo-path issues.60- `scripts/summarize_abinit_run.py`61 Summarize an ABINIT directory or `.abo` output using simple, auditable heuristics.62- `scripts/recommend_abinit_recovery.py`63 Turn incomplete or broken ABINIT stages into concrete restart and parent-child recovery guidance.64- `scripts/export_status_report.py`65 Export a shareable markdown status report from an ABINIT run or staged workflow.66- `scripts/export_input_suggestions.py`67 Export conservative ABINIT input snippets based on detected recovery patterns.6869### 4. Load focused references only when needed7071- ABINIT-specific workflow guidance: `references/abinit.md`72- convergence planning: `references/convergence.md`73- failures and restarts: `references/failure-modes.md`74- scheduler considerations: `references/schedulers.md`7576### 5. Deliver an auditable answer7778Whenever you recommend settings or restart changes, include:7980- the task and parent-child stage assumption81- unresolved physics choices the user still needs to confirm82- exact files that were created or edited83- what output or artifact must exist before the next stage can run8485## Task guardrails8687### Ground-state and relaxation8889- Keep exploratory relaxations numerically sane but not over-tight.90- Separate geometry convergence from production-quality total energies.91- Do not compare final energies from a loose relaxation against a tighter static setup without rerunning consistently.9293### DOS9495- Treat DOS as a child workflow that depends on a trustworthy parent state.96- Use denser k-point sampling for DOS than for a cheap exploratory relaxation.97- Be explicit about whether the stage reads `DEN`, `WFK`, or both.9899### Band structure100101- Require a converged parent stage.102- Do not fabricate a band path; use a symmetry tool or literature reference.103- Keep the band stage read-only with respect to density whenever possible.104105## Quality bar106107- Prefer conservative defaults over flashy guesses.108- Distinguish ABINIT-specific syntax advice from material-specific physics advice.109- Point out when a recommendation is only a heuristic.110- If the output is incomplete or the pseudo policy is unclear, say so directly.